
print("prelim stats")

prelim stats


#import libraries

import csv
import pandas as pd
import numpy as np


#import and read csv file
#display first 10 rows

import pandas as pd
crime_data1 = pd.read_csv(r"C:\Users\radon\Documents\CIND820/crimedata.csv")

crime_data1.head(10)


#display data types of all columns

datatypes = crime_data1.dtypes
print(datatypes)


#replace all missing values with NaN

import pandas as pd
crime_data = pd.read_csv('crimedata.csv', na_values=['?'])
crime_data.head(10)


#check number of rows
len(crime_data)

2215


#check datatypes again

datatypes2 = crime_data.dtypes
print(datatypes2)


#display the sum of all NaN in each column

crime_data.isnull().sum()


#seperate all columns with missing values

null_cols = crime_data[crime_data.columns[crime_data.isna().any()]]
null_cols.head()


#display sums of missing values of only columns that contain missing values

null_list= null_cols.columns.values
null_cols.isnull().sum()


#change settings to display all columns
pd.set_option('display.max_columns', None)

#get summary statistics of all columns
crime_data.describe()


crime_data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2215 entries, 0 to 2214
Columns: 147 entries, communityname to nonViolPerPop
dtypes: float64(116), int64(29), object(2)
memory usage: 2.5+ MB


#find the mean of each column by state
mean_data = crime_data.groupby("state").mean()
mean_data.head()

C:\Users\radon\AppData\Local\Temp\ipykernel_10788\3113613801.py:2: FutureWarning: The default value of numeric_only in DataFrameGroupBy.mean is deprecated. In a future version, numeric_only will default to False. Either specify numeric_only or select only columns which should be valid for the function.
  mean_data = crime_data.groupby("state").mean()


#find the mean of crime per pop columns by state
state_crimes =crime_data.groupby("state")["murdPerPop", "rapesPerPop", "robbbPerPop", "assaultPerPop", "burglPerPop", "larcPerPop", "autoTheftPerPop", "arsonsPerPop"].mean()
state_crimes.head(10)

C:\Users\radon\AppData\Local\Temp\ipykernel_10788\76998245.py:2: FutureWarning: Indexing with multiple keys (implicitly converted to a tuple of keys) will be deprecated, use a list instead.
  state_crimes =crime_data.groupby("state")["murdPerPop", "rapesPerPop", "robbbPerPop", "assaultPerPop", "burglPerPop", "larcPerPop", "autoTheftPerPop", "arsonsPerPop"].mean()


#find the states with min and max values for crimes
state_crimes["murdPerPop"].sort_values()
state_crimes["rapesPerPop"].sort_values()
state_crimes["robbbPerPop"].sort_values()
state_crimes["assaultPerPop"].sort_values()
state_crimes["burglPerPop"].sort_values()
state_crimes["larcPerPop"].sort_values()
state_crimes["autoTheftPerPop"].sort_values()
state_crimes["arsonsPerPop"].sort_values()


#find representation of each state in dataset, how many rows does each state have?
crime_data.groupby(['state'])['state'].count().sort_values()


#Examine the STATE with the overall max values of each crime
crime_data.loc[crime_data['state'] == 'DC']


#Sort the dataset by population
crime_data.sort_values(['population'])


#Subset the states with the most representation in the dataset
max_rep = ['CA', 'NJ', 'TX']
 
maxrep_subset = crime_data[crime_data.state.isin(max_rep)]

maxrep_subset.describe()


#Subset the states with the least representation
min_rep = ['KS', 'DE', 'DC', 'AK', 'VT']
 
minrep_subset = crime_data[crime_data.state.isin(min_rep)]

minrep_subset.describe()


#az = crime_data.loc[crime_data['state'] == "CA"]
#az.boxplot(column="murdPerPop")

#dc = crime_data.loc[crime_data['state']== "DC"]


#after deciding on a NaN ratio threshold, drop the columns which exceed the threshold (50%)

crimedata_reduced= crime_data.drop(['countyCode', 'communityCode', 'fold', 'LemasSwornFT', 'LemasSwFTPerPop', 'LemasSwFTFieldOps', 'LemasSwFTFieldPerPop', 'LemasTotalReq', 'LemasTotReqPerPop', 'PolicReqPerOffic', 'PolicPerPop', 'RacialMatchCommPol', 'PctPolicWhite', 'PctPolicBlack', 'PctPolicHisp', 'PctPolicAsian', 'PctPolicMinor', 'OfficAssgnDrugUnits', 'NumKindsDrugsSeiz', 'PolicAveOTWorked', 'PolicCars', 'PolicOperBudg', 'LemasPctPolicOnPatr', 'LemasGangUnitDeploy', 'PolicBudgPerPop'], axis=1)
crimedata_reduced.head()


#impute missing values
#for columns with very small number of missing values, impute with MODE

crimedata_reduced['burglaries'].fillna(crimedata_reduced['burglaries'].mode()[0], inplace=True)
crimedata_reduced['burglPerPop'].fillna(crimedata_reduced['burglPerPop'].mode()[0], inplace=True)
crimedata_reduced['larcenies'].fillna(crimedata_reduced['larcenies'].mode()[0], inplace=True)
crimedata_reduced['larcPerPop'].fillna(crimedata_reduced['larcPerPop'].mode()[0], inplace=True)
crimedata_reduced['autoTheft'].fillna(crimedata_reduced['autoTheft'].mode()[0], inplace=True)
crimedata_reduced['autoTheftPerPop'].fillna(crimedata_reduced['autoTheftPerPop'].mode()[0], inplace=True)
crimedata_reduced['OtherPerCap'].fillna(crimedata_reduced['OtherPerCap'].mode()[0], inplace=True)
crimedata_reduced['assaults'].fillna(crimedata_reduced['assaults'].mode()[0], inplace=True)
crimedata_reduced['assaultPerPop'].fillna(crimedata_reduced['assaultPerPop'].mode()[0], inplace=True)


#Find out the total counts of how many times each state is represented in the dataset
#With this information, I have chosen to impute by the mean value of the column, aggregated by state

#crimedata_reduced[crimedata_reduced['rapes'].isnull()]
#crimedata_reduced.pivot_table(index = ['state'], aggfunc ='size')

from collections import Counter
print(Counter(crimedata_reduced['state']))

Counter({'CA': 279, 'NJ': 211, 'TX': 162, 'MA': 123, 'OH': 111, 'MI': 108, 'PA': 101, 'FL': 90, 'CT': 71, 'MN': 66, 'WI': 60, 'IN': 48, 'NY': 46, 'NC': 46, 'AL': 43, 'MO': 42, 'WA': 40, 'IL': 40, 'GA': 37, 'OK': 36, 'TN': 35, 'VA': 33, 'OR': 31, 'SC': 28, 'KY': 26, 'RI': 26, 'AR': 25, 'CO': 25, 'UT': 24, 'LA': 22, 'NH': 21, 'MS': 20, 'AZ': 20, 'IA': 20, 'ME': 17, 'WV': 14, 'MD': 12, 'NM': 10, 'SD': 9, 'ND': 8, 'WY': 7, 'ID': 7, 'NV': 5, 'VT': 4, 'AK': 3, 'KS': 1, 'DE': 1, 'DC': 1})


#Separate all rows represented by the state CA, and create a dataframe with them
CA = crimedata_reduced[crimedata_reduced['state']=='CA']
CA_df= pd.DataFrame(CA)

#Check for missing values: return names of each column that carries a missing value
CA_df.columns[CA_df.isna().any()]

#Check the total number of rows represented by the particular state
len(CA_df)

#Check total number of missing values in that column to establish the ratio of missing information that exists here
CA_df['ViolentCrimesPerPop'].isna().sum()

#If the ratio of missing information is not significant, impute the missing values with the mean of that column of its own state
CA_df['ViolentCrimesPerPop'].fillna(CA_df['ViolentCrimesPerPop'].mean(), inplace = True)

#Confirm values were successfully imputed
CA_df.columns[CA_df.isna().any()]

Index([], dtype='object')


#Create a dataframe where we filter out all rows represented by the particular state
ca_filtered = crimedata_reduced[crimedata_reduced['state'] != 'CA']

#Create a new dataframe which will serve as our main, fully imputed dataframe
#In this new dataframe, take the filtered dataframe and append the imputed state dataframe to it
crimedata_new = pd.concat([ca_filtered, CA_df], ignore_index=True)

#Confirm there are no missing values in the rows of the particular state in the new main dataframe
Counter(crimedata_new[crimedata_new['state'] == "CA"].isna().any())

Counter({False: 122})


NJ = crimedata_reduced[crimedata_reduced['state']=='NJ']
NJ_df= pd.DataFrame(NJ)
NJ_df.columns[NJ_df.isna().any()]

Index([], dtype='object')


TX = crimedata_reduced[crimedata_reduced['state']=='TX']
TX_df= pd.DataFrame(TX)
TX_df.columns[TX_df.isna().any()]

len(TX_df)
TX_df['rapes'].isna().sum()
TX_df['rapesPerPop'].isna().sum()
TX_df['arsons'].isna().sum()
TX_df['arsonsPerPop'].isna().sum()
TX_df['ViolentCrimesPerPop'].isna().sum()
TX_df['nonViolPerPop'].isna().sum()

5


TX_df['rapes'].fillna(TX_df['rapes'].mean(), inplace = True)
TX_df['rapesPerPop'].fillna(TX_df['rapesPerPop'].mean(), inplace = True)
TX_df['arsons'].fillna(TX_df['arsons'].mean(), inplace = True)
TX_df['arsonsPerPop'].fillna(TX_df['arsonsPerPop'].mean(), inplace = True)
TX_df['ViolentCrimesPerPop'].fillna(TX_df['ViolentCrimesPerPop'].mean(), inplace = True)
TX_df['nonViolPerPop'].fillna(TX_df['nonViolPerPop'].mean(), inplace = True)

TX_df.columns[TX_df.isna().any()]

tx_filtered = crimedata_reduced[crimedata_reduced['state'] != 'TX']
crimedata_new = pd.concat([tx_filtered, TX_df], ignore_index=True)

Counter(crimedata_new[crimedata_new['state'] == "TX"].isna().any())

Counter({False: 120, True: 2})


MA = crimedata_reduced[crimedata_reduced['state']=='MA']
MA_df= pd.DataFrame(MA)
MA_df.columns[MA_df.isna().any()]

len(MA_df)
MA_df['arsons'].isna().sum()
MA_df['arsonsPerPop'].isna().sum()
MA_df['ViolentCrimesPerPop'].isna().sum()
MA_df['nonViolPerPop'].isna().sum()

7


MA_df['arsons'].fillna(MA_df['arsons'].mean(), inplace = True)
MA_df['arsonsPerPop'].fillna(MA_df['arsonsPerPop'].mean(), inplace = True)
MA_df['ViolentCrimesPerPop'].fillna(MA_df['ViolentCrimesPerPop'].mean(), inplace = True)
MA_df['nonViolPerPop'].fillna(MA_df['nonViolPerPop'].mean(), inplace = True)

MA_df.columns[MA_df.isna().any()]

ma_filtered = crimedata_reduced[crimedata_reduced['state'] != 'MA']
crimedata_new = pd.concat([ma_filtered, MA_df], ignore_index=True)

Counter(crimedata_new[crimedata_new['state'] == "MA"].isna().any())

Counter({False: 122})


OH = crimedata_reduced[crimedata_reduced['state']=='OH']
OH_df= pd.DataFrame(OH)
OH_df.columns[OH_df.isna().any()]

len(OH_df)
OH_df['arsons'].isna().sum()
OH_df['arsonsPerPop'].isna().sum()
OH_df['ViolentCrimesPerPop'].isna().sum()
OH_df['nonViolPerPop'].isna().sum()

3


OH_df['arsons'].fillna(OH_df['arsons'].mean(), inplace = True)
OH_df['arsonsPerPop'].fillna(OH_df['arsonsPerPop'].mean(), inplace = True)
OH_df['ViolentCrimesPerPop'].fillna(OH_df['ViolentCrimesPerPop'].mean(), inplace = True)
OH_df['nonViolPerPop'].fillna(OH_df['nonViolPerPop'].mean(), inplace = True)

OH_df.columns[OH_df.isna().any()]

oh_filtered = crimedata_reduced[crimedata_reduced['state'] != 'OH']
crimedata_new = pd.concat([oh_filtered, OH_df], ignore_index=True)

Counter(crimedata_new[crimedata_new['state'] == "OH"].isna().any())

Counter({False: 122})


MI = crimedata_reduced[crimedata_reduced['state']=='MI']
MI_df= pd.DataFrame(MI)
MI_df.columns[MI_df.isna().any()]

len(MI_df)

#TOTAL rows for MI was 108
#The three columns beneath are missing ALL 108 values in these columns, there are no values to work with in order to impute the mean
MI_df['ViolentCrimesPerPop'].isna().sum()
MI_df['rapes'].isna().sum()
MI_df['rapesPerPop'].isna().sum()

#The following rows are not missing an insignificant amount of values, they can be imputed as planned
MI_df['arsons'].isna().sum()
MI_df['arsonsPerPop'].isna().sum()
MI_df['nonViolPerPop'].isna().sum()

1


#Impute the columns that are appropriate to be imputed by the mean

MI_df['arsons'].fillna(MI_df['arsons'].mean(), inplace = True)
MI_df['arsonsPerPop'].fillna(MI_df['arsonsPerPop'].mean(), inplace = True)
MI_df['nonViolPerPop'].fillna(MI_df['nonViolPerPop'].mean(), inplace = True)

MI_df.columns[MI_df.isna().any()]

mi_filtered = crimedata_reduced[crimedata_reduced['state'] != 'MI']
crimedata_new = pd.concat([mi_filtered, MI_df], ignore_index=True)

Counter(crimedata_new[crimedata_new['state'] == "MI"].isna().any())
MI_df.columns[MI_df.isna().any()]

#There are still 3 columns that have not been addressed
#These columns must be revisited

Index(['rapes', 'rapesPerPop', 'ViolentCrimesPerPop'], dtype='object')


PA = crimedata_reduced[crimedata_reduced['state']=='PA']
PA_df= pd.DataFrame(PA)
PA_df.columns[PA_df.isna().any()]

len(PA_df)
PA_df['arsons'].isna().sum()
PA_df['arsonsPerPop'].isna().sum()
PA_df['nonViolPerPop'].isna().sum()

1


PA_df['arsons'].fillna(PA_df['arsons'].mean(), inplace = True)
PA_df['arsonsPerPop'].fillna(PA_df['arsonsPerPop'].mean(), inplace = True)
PA_df['nonViolPerPop'].fillna(PA_df['nonViolPerPop'].mean(), inplace = True)

PA_df.columns[PA_df.isna().any()]

pa_filtered = crimedata_reduced[crimedata_reduced['state'] != 'PA']
crimedata_new = pd.concat([pa_filtered, PA_df], ignore_index=True)

Counter(crimedata_new[crimedata_new['state'] == "PA"].isna().any())

Counter({False: 122})


FL = crimedata_reduced[crimedata_reduced['state']=='FL']
FL_df= pd.DataFrame(FL)
FL_df.columns[FL_df.isna().any()]

Index([], dtype='object')


CT = crimedata_reduced[crimedata_reduced['state']=='CT']
CT_df= pd.DataFrame(CT)
CT_df.columns[CT_df.isna().any()]

len(CT_df)
CT_df['ViolentCrimesPerPop'].isna().sum()

2


CT_df['ViolentCrimesPerPop'].fillna(CT_df['ViolentCrimesPerPop'].mean(), inplace = True)

CT_df.columns[CT_df.isna().any()]

ct_filtered = crimedata_reduced[crimedata_reduced['state'] != 'CT']
crimedata_new = pd.concat([ct_filtered, CT_df], ignore_index=True)

Counter(crimedata_new[crimedata_new['state'] == "CT"].isna().any())

Counter({False: 122})


MN = crimedata_reduced[crimedata_reduced['state']=='MN']
MN_df= pd.DataFrame(MN)
MN_df.columns[CA_df.isna().any()]

Index([], dtype='object')


WI = crimedata_reduced[crimedata_reduced['state']=='WI']
WI_df= pd.DataFrame(WI)
WI_df.columns[WI_df.isna().any()]

len(WI_df)
WI_df['arsons'].isna().sum()
WI_df['arsonsPerPop'].isna().sum()
WI_df['nonViolPerPop'].isna().sum()

1


WI_df['arsons'].fillna(WI_df['arsons'].mean(), inplace = True)
WI_df['arsonsPerPop'].fillna(WI_df['arsonsPerPop'].mean(), inplace = True)
WI_df['nonViolPerPop'].fillna(WI_df['nonViolPerPop'].mean(), inplace = True)

WI_df.columns[WI_df.isna().any()]

wi_filtered = crimedata_reduced[crimedata_reduced['state'] != 'WI']
crimedata_new = pd.concat([wi_filtered, WI_df], ignore_index=True)

Counter(crimedata_new[crimedata_new['state'] == "WI"].isna().any())

Counter({False: 122})


IN = crimedata_reduced[crimedata_reduced['state']=='IN']
IN_df= pd.DataFrame(IN)
IN_df.columns[IN_df.isna().any()]

Index([], dtype='object')


NY = crimedata_reduced[crimedata_reduced['state']=='NY']
NY_df= pd.DataFrame(NY)
NY_df.columns[NY_df.isna().any()]

len(NY_df)
NY_df['arsons'].isna().sum()
NY_df['arsonsPerPop'].isna().sum()
NY_df['nonViolPerPop'].isna().sum()

17


NY_df['arsons'].fillna(NY_df['arsons'].mean(), inplace = True)
NY_df['arsonsPerPop'].fillna(NY_df['arsonsPerPop'].mean(), inplace = True)
NY_df['nonViolPerPop'].fillna(NY_df['nonViolPerPop'].mean(), inplace = True)

NY_df.columns[NY_df.isna().any()]

ny_filtered = crimedata_reduced[crimedata_reduced['state'] != 'NY']
crimedata_new = pd.concat([ny_filtered, NY_df], ignore_index=True)

Counter(crimedata_new[crimedata_new['state'] == "NY"].isna().any())

Counter({False: 122})


NC = crimedata_reduced[crimedata_reduced['state']=='NC']
NC_df= pd.DataFrame(NC)
NC_df.columns[NC_df.isna().any()]

Index([], dtype='object')


AL = crimedata_reduced[crimedata_reduced['state']=='AL']
AL_df= pd.DataFrame(AL)
AL_df.columns[AL_df.isna().any()]

len(AL_df)
AL_df['arsons'].isna().sum()
AL_df['arsonsPerPop'].isna().sum()
AL_df['nonViolPerPop'].isna().sum()

len(AL_df)

43


AL_df['arsons'].fillna(AL_df['arsons'].mean(), inplace = True)
AL_df['arsonsPerPop'].fillna(AL_df['arsonsPerPop'].mean(), inplace = True)
AL_df['nonViolPerPop'].fillna(AL_df['nonViolPerPop'].mean(), inplace = True)

AL_df.columns[AL_df.isna().any()]

al_filtered = crimedata_reduced[crimedata_reduced['state'] != 'AL']
crimedata_new = pd.concat([al_filtered, AL_df], ignore_index=True)

Counter(crimedata_new[crimedata_new['state'] == "AL"].isna().any())

Counter({False: 122})


MO = crimedata_reduced[crimedata_reduced['state']=='MO']
MO_df= pd.DataFrame(MO)
MO_df.columns[MO_df.isna().any()]

Index([], dtype='object')


WA = crimedata_reduced[crimedata_reduced['state']=='WA']
WA_df= pd.DataFrame(WA)
WA_df.columns[WA_df.isna().any()]

len(WA_df)
WA_df['arsons'].isna().sum()
WA_df['arsonsPerPop'].isna().sum()
WA_df['nonViolPerPop'].isna().sum()

1


WA_df['arsons'].fillna(WA_df['arsons'].mean(), inplace = True)
WA_df['arsonsPerPop'].fillna(WA_df['arsonsPerPop'].mean(), inplace = True)
WA_df['nonViolPerPop'].fillna(WA_df['nonViolPerPop'].mean(), inplace = True)

WA_df.columns[WA_df.isna().any()]

wa_filtered = crimedata_reduced[crimedata_reduced['state'] != 'WA']
crimedata_new = pd.concat([wa_filtered, WA_df], ignore_index=True)

Counter(crimedata_new[crimedata_new['state'] == "WA"].isna().any())

Counter({False: 122})


IL = crimedata_reduced[crimedata_reduced['state']=='IL']
IL_df= pd.DataFrame(IL)
IL_df.columns[IL_df.isna().any()]

len(IL_df)
IL_df['rapes'].isna().sum()
IL_df['rapesPerPop'].isna().sum()
IL_df['ViolentCrimesPerPop'].isna().sum()

40


GA = crimedata_reduced[crimedata_reduced['state']=='GA']
GA_df= pd.DataFrame(GA)
GA_df.columns[GA_df.isna().any()]

Index([], dtype='object')


OK = crimedata_reduced[crimedata_reduced['state']=='OK']
OK_df= pd.DataFrame(OK)
OK_df.columns[OK_df.isna().any()]

Index([], dtype='object')


TN = crimedata_reduced[crimedata_reduced['state']=='TN']
TN_df= pd.DataFrame(TN)
TN_df.columns[TN_df.isna().any()]

len(TN_df)
TN_df['arsons'].isna().sum()
TN_df['arsonsPerPop'].isna().sum()
TN_df['nonViolPerPop'].isna().sum()

2


TN_df['arsons'].fillna(TN_df['arsons'].mean(), inplace = True)
TN_df['arsonsPerPop'].fillna(TN_df['arsonsPerPop'].mean(), inplace = True)
TN_df['nonViolPerPop'].fillna(TN_df['nonViolPerPop'].mean(), inplace = True)

TN_df.columns[WA_df.isna().any()]

tn_filtered = crimedata_reduced[crimedata_reduced['state'] != 'TN']
crimedata_new = pd.concat([tn_filtered, TN_df], ignore_index=True)

Counter(crimedata_new[crimedata_new['state'] == "TN"].isna().any())

Counter({False: 122})


VA = crimedata_reduced[crimedata_reduced['state']=='VA']
VA_df= pd.DataFrame(VA)
VA_df.columns[VA_df.isna().any()]

Index([], dtype='object')


OR = crimedata_reduced[crimedata_reduced['state']=='OR']
OR_df= pd.DataFrame(OR)
OR_df.columns[OR_df.isna().any()]

Index([], dtype='object')


SC = crimedata_reduced[crimedata_reduced['state']=='SC']
SC_df= pd.DataFrame(SC)
SC_df.columns[SC_df.isna().any()]

Index([], dtype='object')


KY = crimedata_reduced[crimedata_reduced['state']=='KY']
KY_df= pd.DataFrame(KY)
KY_df.columns[KY_df.isna().any()]

Index([], dtype='object')


RI = crimedata_reduced[crimedata_reduced['state']=='RI']
RI_df= pd.DataFrame(RI)
RI_df.columns[RI_df.isna().any()]

Index([], dtype='object')


AR = crimedata_reduced[crimedata_reduced['state']=='AR']
AR_df= pd.DataFrame(AR)
AR_df.columns[AR_df.isna().any()]

Index([], dtype='object')


CO = crimedata_reduced[crimedata_reduced['state']=='CO']
CO_df= pd.DataFrame(CO)
CO_df.columns[CO_df.isna().any()]

Index([], dtype='object')


UT = crimedata_reduced[crimedata_reduced['state']=='UT']
UT_df= pd.DataFrame(UT)
UT_df.columns[UT_df.isna().any()]

Index([], dtype='object')


LA = crimedata_reduced[crimedata_reduced['state']=='LA']
LA_df= pd.DataFrame(LA)
LA_df.columns[LA_df.isna().any()]

len(LA_df)
LA_df['arsons'].isna().sum()
LA_df['arsonsPerPop'].isna().sum()
LA_df['nonViolPerPop'].isna().sum()

3


LA_df['arsons'].fillna(LA_df['arsons'].mean(), inplace = True)
LA_df['arsonsPerPop'].fillna(LA_df['arsonsPerPop'].mean(), inplace = True)
LA_df['nonViolPerPop'].fillna(LA_df['nonViolPerPop'].mean(), inplace = True)

LA_df.columns[LA_df.isna().any()]

la_filtered = crimedata_reduced[crimedata_reduced['state'] != 'LA']
crimedata_new = pd.concat([la_filtered, LA_df], ignore_index=True)

Counter(crimedata_new[crimedata_new['state'] == "LA"].isna().any())

Counter({False: 122})


NH = crimedata_reduced[crimedata_reduced['state']=='NH']
NH_df= pd.DataFrame(NH)
NH_df.columns[NH_df.isna().any()]

Index([], dtype='object')


MS = crimedata_reduced[crimedata_reduced['state']=='MS']
MS_df= pd.DataFrame(MS)
MS_df.columns[MS_df.isna().any()]

len(MS_df)
MS_df['ViolentCrimesPerPop'].isna().sum()

1


MS_df['ViolentCrimesPerPop'].fillna(MS_df['ViolentCrimesPerPop'].mean(), inplace = True)

MS_df.columns[MS_df.isna().any()]

ms_filtered = crimedata_reduced[crimedata_reduced['state'] != 'MS']
crimedata_new = pd.concat([ms_filtered, MS_df], ignore_index=True)

Counter(crimedata_new[crimedata_new['state'] == "MS"].isna().any())

Counter({False: 122})


AZ = crimedata_reduced[crimedata_reduced['state']=='AZ']
AZ_df= pd.DataFrame(AZ)
AZ_df.columns[AZ_df.isna().any()]

Index([], dtype='object')


IA = crimedata_reduced[crimedata_reduced['state']=='IA']
IA_df= pd.DataFrame(IA)
IA_df.columns[IA_df.isna().any()]

len(IA_df)
IA_df['arsons'].isna().sum()
IA_df['arsonsPerPop'].isna().sum()
IA_df['nonViolPerPop'].isna().sum()

17


ME = crimedata_reduced[crimedata_reduced['state']=='ME']
ME_df= pd.DataFrame(ME)
ME_df.columns[ME_df.isna().any()]

Index([], dtype='object')


WV = crimedata_reduced[crimedata_reduced['state']=='WV']
WV_df= pd.DataFrame(WV)
WV_df.columns[WV_df.isna().any()]

Index([], dtype='object')


MD = crimedata_reduced[crimedata_reduced['state']=='MD']
MD_df= pd.DataFrame(MD)
MD_df.columns[MD_df.isna().any()]

len(MD_df)
MD_df['arsons'].isna().sum()
MD_df['arsonsPerPop'].isna().sum()
MD_df['nonViolPerPop'].isna().sum()

3


MD_df['arsons'].fillna(MD_df['arsons'].mean(), inplace = True)
MD_df['arsonsPerPop'].fillna(MD_df['arsonsPerPop'].mean(), inplace = True)
MD_df['nonViolPerPop'].fillna(MD_df['nonViolPerPop'].mean(), inplace = True)

MD_df.columns[MD_df.isna().any()]

md_filtered = crimedata_reduced[crimedata_reduced['state'] != 'MD']
crimedata_new = pd.concat([md_filtered, MD_df], ignore_index=True)

Counter(crimedata_new[crimedata_new['state'] == "MD"].isna().any())

Counter({False: 122})


NM = crimedata_reduced[crimedata_reduced['state']=='NM']
NM_df= pd.DataFrame(NM)
NM_df.columns[NM_df.isna().any()]

Index([], dtype='object')


SD = crimedata_reduced[crimedata_reduced['state']=='SD']
SD_df= pd.DataFrame(SD)
SD_df.columns[SD_df.isna().any()]

len(SD_df)
SD_df['arsons'].isna().sum()
SD_df['arsonsPerPop'].isna().sum()
SD_df['nonViolPerPop'].isna().sum()

1


SD_df['arsons'].fillna(SD_df['arsons'].mean(), inplace = True)
SD_df['arsonsPerPop'].fillna(SD_df['arsonsPerPop'].mean(), inplace = True)
SD_df['nonViolPerPop'].fillna(SD_df['nonViolPerPop'].mean(), inplace = True)

SD_df.columns[SD_df.isna().any()]

sd_filtered = crimedata_reduced[crimedata_reduced['state'] != 'SD']
crimedata_new = pd.concat([sd_filtered, SD_df], ignore_index=True)

Counter(crimedata_new[crimedata_new['state'] == "SD"].isna().any())

Counter({False: 122})


ND = crimedata_reduced[crimedata_reduced['state']=='ND']
ND_df= pd.DataFrame(ND)
ND_df.columns[ND_df.isna().any()]

Index([], dtype='object')


WY = crimedata_reduced[crimedata_reduced['state']=='WY']
WY_df= pd.DataFrame(WY)
WY_df.columns[WY_df.isna().any()]

Index([], dtype='object')


ID = crimedata_reduced[crimedata_reduced['state']=='ID']
ID_df= pd.DataFrame(ID)
ID_df.columns[ID_df.isna().any()]

Index([], dtype='object')


NY = crimedata_reduced[crimedata_reduced['state']=='NY']
NY_df= pd.DataFrame(NY)
NY_df.columns[NY_df.isna().any()]

len(NY_df)
NY_df['arsons'].isna().sum()
NY_df['arsonsPerPop'].isna().sum()
NY_df['nonViolPerPop'].isna().sum()

17


NY_df['arsons'].fillna(NY_df['arsons'].mean(), inplace = True)
NY_df['arsonsPerPop'].fillna(NY_df['arsonsPerPop'].mean(), inplace = True)
NY_df['nonViolPerPop'].fillna(NY_df['nonViolPerPop'].mean(), inplace = True)

NY_df.columns[NY_df.isna().any()]

ny_filtered = crimedata_reduced[crimedata_reduced['state'] != 'NY']
crimedata_new = pd.concat([ny_filtered, NY_df], ignore_index=True)

Counter(crimedata_new[crimedata_new['state'] == "NY"].isna().any())

Counter({False: 122})


VT = crimedata_reduced[crimedata_reduced['state']=='VT']
VT_df= pd.DataFrame(VT)
VT_df.columns[VT_df.isna().any()]

len(VT_df)
VT_df['arsons'].isna().sum()
VT_df['arsonsPerPop'].isna().sum()
VT_df['nonViolPerPop'].isna().sum()

len(VT_df)

4


AK = crimedata_reduced[crimedata_reduced['state']=='AK']
AK_df= pd.DataFrame(AK)
AK_df.columns[AK_df.isna().any()]

Index([], dtype='object')


KS = crimedata_reduced[crimedata_reduced['state']=='KS']
KS_df= pd.DataFrame(KS)
KS_df.columns[KS_df.isna().any()]

len(KS_df)
KS_df['arsons'].isna().sum()
KS_df['arsonsPerPop'].isna().sum()
KS_df['nonViolPerPop'].isna().sum()

len(KS_df)

1


DE = crimedata_reduced[crimedata_reduced['state']=='DE']
DE_df= pd.DataFrame(DE)
DE_df.columns[DE_df.isna().any()]

Index([], dtype='object')


DC = crimedata_reduced[crimedata_reduced['state']=='DC']
DC_df= pd.DataFrame(DC)
DC_df.columns[DC_df.isna().any()]

Index([], dtype='object')


#Check the total number of missing values for each column that was reported to have missing values

crimedata_new['rapes'].isna().sum()
crimedata_new['rapesPerPop'].isna().sum()
crimedata_new['arsons'].isna().sum()
crimedata_new['arsonsPerPop'].isna().sum()
crimedata_new['nonViolPerPop'].isna().sum()

80


#DROP ALL ROWS WITH MISSING VALUES
crimedata_new = crimedata_new.dropna()


#Check whole dataset for columns with missing values
crimedata_new.columns[crimedata_new.isna().any()]

len(crimedata_new)

1919


#Check datatypes again to confirm
crimedata_new.dtypes


print(crimedata_new['murdPerPop'].min())
print(crimedata_new['murdPerPop'].max())

0.0
91.09


print(crimedata_new['robbbPerPop'].min())
print(crimedata_new['robbbPerPop'].max())

0.0
2264.13


pd.set_option('display.max_rows', None)

#Run correlation matrix
crime_corr = crimedata_new.corr(numeric_only=True)


import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt

plt.figure(figsize=(30, 10))
sns.heatmap(crime_corr)

<AxesSubplot:>


#Unstack the matrix and sort the values from lowest to highest so we can clearly see the most negatively and positively correlated pairs
sorted_mat = crime_corr.unstack().sort_values()
sorted_mat


#Create dataset for the specific crime target variable

murders_data = crimedata_new.drop(['rapes', 'rapesPerPop', 'robberies', 'robbbPerPop', 'assaults', 'assaultPerPop', 
                                   'burglaries', 'burglPerPop', 'larcenies', 'larcPerPop', 'autoTheft', 'autoTheftPerPop', 
                                   'arsons', 'arsonsPerPop', 'ViolentCrimesPerPop', 'nonViolPerPop'], axis=1)
murders_data.head()


for col in murders_data.columns:
    print(col)


plt.figure(figsize=(30, 10))
heatmap = sns.heatmap(murders_data.corr(), vmin=-1, vmax=1, annot=True)

C:\Users\radon\AppData\Local\Temp\ipykernel_10788\312952547.py:2: FutureWarning: The default value of numeric_only in DataFrame.corr is deprecated. In a future version, it will default to False. Select only valid columns or specify the value of numeric_only to silence this warning.
  heatmap = sns.heatmap(murders_data.corr(), vmin=-1, vmax=1, annot=True)


#Examine the correlations of each column with 'murdPerPop' as our target variable
murdPerPop_corr = murders_data[murders_data.columns[1:]].corr()['murdPerPop'][:]

#Sort the values so we can see the positive and negative correlation clearly
murdPerPop_corr.sort_values()


#Examine the correlations of each columns and 'murders' as our target variable
murders_corr = murders_data[murders_data.columns[1:]].corr()['murders'][:]

#Sort the values so we can see the positive and negative correlations clearly
murders_corr.sort_values()


#murd_corr = murders_data.corr(method='spearman')

#Create a correlation matrix for the dataframe category
murd_corr = murders_data.corr(numeric_only=True).abs()

#Select the upper triangle of the matrix, excluding the diagnonal elements
murd_tri = murd_corr.where(np.triu(np.ones(murd_corr.shape),k=1).astype(bool))

#drop the columns with a correlation greater than 0.8 and make a list of those columns named 'murd_drop'
murd_drop = [column for column in murd_tri.columns if any(murd_tri[column] > 0.8)]

#drop the murd_drop columns from the dataframe
murders = murders_data.drop(murders_data[murd_drop], axis=1)


#for col in murders.columns:
    #print(col)

len(murders.columns)

53


robberies_data = crimedata_new.drop(['rapes', 'rapesPerPop', 'murders', 'murdPerPop', 'assaults', 'assaultPerPop', 'burglaries', 'burglPerPop', 'larcenies', 'larcPerPop', 'autoTheft', 'autoTheftPerPop', 'arsons', 'arsonsPerPop', 'ViolentCrimesPerPop', 'nonViolPerPop'], axis=1)
robberies_data.head()


robberies_data.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 1919 entries, 0 to 2214
Columns: 106 entries, communityname to robbbPerPop
dtypes: float64(77), int64(27), object(2)
memory usage: 1.6+ MB


plt.figure(figsize=(30, 10))
sns.heatmap(robberies_data.corr(), vmin=-1, vmax=1, annot=True)

C:\Users\radon\AppData\Local\Temp\ipykernel_10788\1798950277.py:2: FutureWarning: The default value of numeric_only in DataFrame.corr is deprecated. In a future version, it will default to False. Select only valid columns or specify the value of numeric_only to silence this warning.
  sns.heatmap(robberies_data.corr(), vmin=-1, vmax=1, annot=True)

<AxesSubplot:>


#Examine the correlations of each columns and 'robbbPerPop' as our target variable
robbbPerPop_corr = robberies_data[robberies_data.columns[1:]].corr()['robbbPerPop'][:]

#Sort the values so we can see the positive and negative correlations clearly
robbbPerPop_corr.sort_values()


#Examine the correlations of each columns and 'robberies' as our target variable
robberies_corr = robberies_data[robberies_data.columns[1:]].corr()['robberies'][:]

#Sort the values so we can see the positive and negative correlations clearly
robberies_corr.sort_values()


#Create a correlation matrix for the dataframe category
robb_corr = robberies_data.corr(numeric_only=True).abs()

#Select the upper triangle of the matrix, excluding the diagnonal elements
robb_tri = robb_corr.where(np.triu(np.ones(robb_corr.shape),k=1).astype(bool))

#drop the columns with a correlation greater than 0.8 and make a list of those columns
robb_drop = [column for column in robb_tri.columns if any(robb_tri[column] > 0.8)]

#drop the columns in the previous list from the dataframe
robberies = robberies_data.drop(robberies_data[robb_drop], axis=1)

robberies.head()


robberies[robberies.columns[1:]].corr()['robbbPerPop'][:]


murders_copy[murders_copy.columns[1:]].corr()['murdPerPop'][:]


#Create a correlation matrix for the dataframe category
murd_corr2 = murders_data.corr(numeric_only=True).abs()

#Select the upper triangle of the matrix, excluding the diagnonal elements
murd_tri2 = murd_corr2.where(np.triu(np.ones(murd_corr.shape),k=1).astype(bool))

#drop the columns with a correlation greater than 0.8 and make a list of those columns named 'murd_drop'
murd_drop2 = [column for column in murd_tri2.columns if any(murd_tri2[column] > 0.8)]

#drop the murd_drop columns from the dataframe
murders_copy = murders_data.drop(murders_data[murd_drop2], axis=1)

murders_copy.head()


#Examine the summaries of each attribute 
murders.describe()


#Check the skew values of all attributes, sort them in ascending order
murders.skew(numeric_only=True).sort_values()


#Find square root to establish how many bins are appropriate
import math
len(murders)
math.sqrt(2215)

#Plot the distribution
import matplotlib.pyplot as plt
murders['population'].hist(bins=20)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['population'].min())
print(murders['population'].max())

#Determine bins based on quantiles
pop_bins = pd.qcut(murders['population'], q=5)
#Check the value counts of each bin to ensure they are balanced
pop_bins.value_counts()

#Create bin labels
pop_bin_labels = ['10000-13500', '13500-19000', '19000-29000', '29000-51500', '515000-7500000']
#Create bins
pop_bin = [10000, 13500, 19000, 29000, 51500, 7500000] 
#Add new category
murders['pop_bins'] = pd.cut(murders['population'], bins=pop_bin, labels=pop_bin_labels)

murders.head()

10005
7322564


murders['pop_bins'].value_counts()

10000-13500       410
13500-19000       387
515000-7500000    384
19000-29000       382
29000-51500       356
Name: pop_bins, dtype: int64


murders['householdsize'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()

#SHAPIRO TEST HERE


# apply normalization technique, using a range of [0,1]
murders['householdsize_bins'] = (murders['householdsize'] - murders['householdsize'].min()) / (murders['householdsize'].max() - murders['householdsize'].min())    
  
murders.head()


murders['racepctblack'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['racepctblack'].min())
print(murders['racepctblack'].max())

#Determine bins based on quantiles
racepctblack_bins = pd.qcut(murders['racepctblack'], q=4)
#Check the value counts of each bin to ensure they are balanced
racepctblack_bins.value_counts()

#Create bin labels
racepctblack_bin_labels = ['0-0.8%', '0.9-2.8%', '2.9-11.1%', '11.2-97%']

#Create new bin category
murders['racepctblack_bins'] = pd.qcut(murders['racepctblack'],
                              q=4,
                              labels=racepctblack_bin_labels)

murders.head()

0.0
96.67


murders['racepctblack_bins'].value_counts()

0-0.8%       484
11.2-97%     480
2.9-11.1%    479
0.9-2.8%     476
Name: racepctblack_bins, dtype: int64


murders['racePctWhite'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['racePctWhite'].min())
print(murders['racePctWhite'].max())

#Determine bins based on quantiles
racePctWhite_= pd.qcut(murders['racePctWhite'], q=4)
#Check the value counts of each bin to ensure they are balanced
racePctWhite_.value_counts()

#Create bin labels
racePctWhite_labels = ['0.0-75%','75-90%', '90-96%', '96-100%']
#Create bins
racePctWhite_bin = [0, 75, 90, 96, 100]
#Add new category
#murders_backup = murders
murders['racePctWhite_bins'] = pd.cut(murders['racePctWhite'], bins=racePctWhite_bin, labels=racePctWhite_labels)

#murders.head()

2.68
99.63


murders['racePctWhite_bins'].value_counts()

75-90%     518
96-100%    474
90-96%     467
0.0-75%    460
Name: racePctWhite_bins, dtype: int64


murders['racePctAsian'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['racePctAsian'].min())
print(murders['racePctAsian'].max())


#Determine bins based on quantiles
racePctAsian_bins = pd.qcut(murders['racePctAsian'], q=4)
#Check the value counts of each bin to ensure they are balanced
racePctAsian_bins.value_counts()

#Create bin labels
racePctAsian_bin_labels = ['0.0-0.6%', '0.6-1.2%', '1.2-2.6%', '2.7-57.5%']

#Create new bin category
murders_backup = murders
murders['racePctAsian_bins'] = pd.qcut(murders['racePctAsian'],
                              q=4,
                              labels=racePctAsian_bin_labels)
#murders.head()

0.06
57.46


murders['racePctAsian_bins'].value_counts()

0.0-0.6%     480
0.6-1.2%     480
2.7-57.5%    480
1.2-2.6%     479
Name: racePctAsian_bins, dtype: int64


murders[' racePctHisp'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders[' racePctHisp'].min())
print(murders[' racePctHisp'].max())

#Determine bins based on quantiles
racePctHisp_bins = pd.qcut(murders[' racePctHisp'], q=4)
#Check the value counts of each bin to ensure they are balanced
racePctHisp_bins.value_counts()

#Create bin labels
racePctHisp_bin_labels = ['0.1-0.9%', '0.9-2.2%', '2.2-7.8%', '7.8-95.3%']

#Create new bin category
murders['racePctHisp_bins'] = pd.qcut(murders[' racePctHisp'],
                              q=4,
                              labels=racePctHisp_bin_labels)
murders.head()


murders['racePctHisp_bins'].value_counts()

0.1-0.9%     485
2.2-7.8%     480
7.8-95.3%    479
0.9-2.2%     475
Name: racePctHisp_bins, dtype: int64


murders['agePct12t21'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


# apply normalization technique, using a range of [0,1]
murders['agePct12t21_norm'] = (murders['agePct12t21'] - murders['agePct12t21'].min()) / (murders['agePct12t21'].max() - murders['agePct12t21'].min())    
  
murders.head()


murders = murders.drop(['householdsize_bins', 'agePct12t21_bins'], axis=1)


murders[' agePct65up'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


# apply normalization technique, using a range of [0,1]
murders['agePct65up_norm'] = (murders[' agePct65up'] - murders[' agePct65up'].min()) / (murders[' agePct65up'].max() - murders[' agePct65up'].min())    
  
murders.head()


murders = murders.drop(['agePct65up_bins'], axis=1)


murders[' pctUrban'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders[' pctUrban'].min())
print(murders[' pctUrban'].max())

#Determine bins based on quantiles
print(murders[' pctUrban'].describe())

#Create bin labels
pctUrban_bin_labels = ['0.0%', '0.1-99%', '100%']
#Create bins
pctUrban_bin = [-1, 0.1, 99, 100]
#Add new category
murders_backup = murders
murders['pctUrban_bins'] = pd.cut(murders[' pctUrban'], bins=pctUrban_bin, labels=pctUrban_bin_labels)
murders.head()

0.0
100.0
count    1919.000000
mean       69.758046
std        44.375875
min         0.000000
25%         0.000000
50%       100.000000
75%       100.000000
max       100.000000
Name:  pctUrban, dtype: float64


murders['pctUrban_bins'].value_counts()

#This distribution was not able to be balanced in any meaningful way
#I decided to leave the values as is, changing them to a binary yes/no would have been unbalanced and would have lost more information

100%       1158
0.0%        532
0.1-99%     229
Name: pctUrban_bins, dtype: int64


murders[' medIncome'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders[' medIncome'].min())
print(murders[' medIncome'].max())

#Determine bins based on quantiles
medIncome_ = pd.qcut(murders[' medIncome'], q=4)
#Check the value counts of each bin to ensure they are balanced
medIncome_.value_counts()

#Create bin labels
medIncome_labels = ['$8,000-$24,000', '$24,000-$32,000', '$32,000-$42,000', '42,000-$125,000']
#Create bins
medIncome_bin = [8865, 24000, 32000, 42000, 123625]
#Add new category
murders_backup = murders
murders['medIncome_bins'] = pd.cut(murders[' medIncome'], bins=medIncome_bin, labels=medIncome_labels)
murders.head()

12908
123625


murders['medIncome_bins'].value_counts()

$24,000-$32,000    511
$8,000-$24,000     500
42,000-$125,000    458
$32,000-$42,000    450
Name: medIncome_bins, dtype: int64


murders['pctWFarmSelf'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['pctWFarmSelf'].min())
print(murders['pctWFarmSelf'].max())

#Determine bins based on quantiles
murders['pctWFarmSelf'].describe()

#Create bin labels
pctWFarmSelf_labels = ['0-0.5%', '0.5-0.7%', '0.7-1.0%', '1.0-7.0%']
#Create bins
pctWFarmSelf_bin = [-1, 0.5, 0.7, 1, 7]
#Add new category
murders['pctWFarmSelf_bins'] = pd.cut(murders['pctWFarmSelf'], bins=pctWFarmSelf_bin, labels=pctWFarmSelf_labels)
murders.head()

0.0
6.53


murders['pctWFarmSelf_bins'].value_counts()

0-0.5%      578
1.0-7.0%    553
0.5-0.7%    401
0.7-1.0%    387
Name: pctWFarmSelf_bins, dtype: int64


murders['pctWInvInc'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


# apply normalization technique, using a range of [0,1]
murders['pctWInvInc_norm'] = (murders['pctWInvInc'] - murders['pctWInvInc'].min()) / (murders['pctWInvInc'].max() - murders['pctWInvInc'].min())    
  
murders.head()


murders[' pctWPubAsst'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders[' pctWPubAsst'].min())
print(murders[' pctWPubAsst'].max())

#Determine bins based on quantiles
pctWPubAsst_ = pd.qcut(murders[' pctWPubAsst'], q=4)
#Check the value counts of each bin to ensure they are balanced
pctWPubAsst_.value_counts()

#Create bin labels
pctWPubAsst_labels = ['0-3%', '3-5%', '5-8%', '8-45%']
#Create bins
pctWPubAsst_bin = [0, 3, 5, 8.5, 45]
#Add new category
murders['pctWPubAsst_bins'] = pd.cut(murders[' pctWPubAsst'], bins=pctWPubAsst_bin, labels=pctWPubAsst_labels)
murders.head()

0.5
26.92


murders['pctWPubAsst_bins'].value_counts()

8-45%    552
5-8%     532
3-5%     441
0-3%     394
Name: pctWPubAsst_bins, dtype: int64


murders['pctWRetire'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


# apply normalization technique, using a range of [0,1]
murders['pctWRetire_norm'] = (murders['pctWRetire'] - murders['pctWRetire'].min()) / (murders['pctWRetire'].max() - murders['pctWRetire'].min())    
  
murders.head()


murders['blackPerCap'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['blackPerCap'].min())
print(murders['blackPerCap'].max())

#Determine bins based on quantiles
blackPerCap_ = pd.qcut(murders['blackPerCap'], q=4)
#Check the value counts of each bin to ensure they are balanced
blackPerCap_.value_counts()

#Create bin labels
blackPerCap_labels = ['0-7000', '6500-10000', '10000-15000', '15000-250000']
#Create bins
blackPerCap_bin = [-1, 7000, 10000, 15000, 250000]
#Add new catrgory
murders['blackPerCap_bins'] = pd.cut(murders['blackPerCap'], bins=blackPerCap_bin, labels=blackPerCap_labels)
murders.head()

0
212120


murders['blackPerCap_bins'].value_counts()

0-7000          536
10000-15000     498
6500-10000      449
15000-250000    436
Name: blackPerCap_bins, dtype: int64


murders['indianPerCap'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['indianPerCap'].min())
print(murders['indianPerCap'].max())

#Determine bins based on quantiles
indianPerCap_ = pd.qcut(murders['indianPerCap'], q=4)
#Check the value counts of each bin to ensure they are balanced
indianPerCap_.value_counts()

#Create bin labels
indianPerCap_labels = ['0-6500', '6500-10000', '10000-15000', '15000-500000']
#Create bins
indianPerCap_bin = [-1, 6500, 10000, 15000, 500000]
#Add new category
murders['indianPerCap_bins'] = pd.cut(murders['indianPerCap'], bins=indianPerCap_bin, labels=indianPerCap_labels)
murders.head()

0
480000


murders['indianPerCap_bins'].value_counts()

0-6500          497
10000-15000     481
6500-10000      474
15000-500000    467
Name: indianPerCap_bins, dtype: int64


murders['AsianPerCap'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['AsianPerCap'].min())
print(murders['AsianPerCap'].max())

#Determine bins based on quantiles
AsianPerCap_ = pd.qcut(murders['AsianPerCap'], q=4)
#Check the value counts of each bin to ensure they are balanced
AsianPerCap_.value_counts()

#Create bin labels
AsianPerCap_labels = ['0-8500', '8500-12500', '12500-17500', '17500-106500']
#Create bins
AsianPerCap_bin = [-1, 8500, 12500, 17500, 106500]
#Add new category
murders['AsianPerCap_bins'] = pd.cut(murders['AsianPerCap'], bins=AsianPerCap_bin, labels=AsianPerCap_labels)
murders.head()

0
106165


murders['AsianPerCap_bins'].value_counts()

8500-12500      501
17500-106500    477
0-8500          476
12500-17500     465
Name: AsianPerCap_bins, dtype: int64


murders['OtherPerCap'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['OtherPerCap'].min())
print(murders['OtherPerCap'].max())

#Determine bins based on quantiles
OtherPerCap_ = pd.qcut(murders['OtherPerCap'], q=4)
#Check the value counts of each bin to ensure they are balanced
OtherPerCap_.value_counts()

#Create bin labels
OtherPerCap_labels = ['0-5500', '5500-8000', '8000-11500', '11500-137000']
#Create bins
OtherPerCap_bin = [-1, 5500, 8000, 11500, 137000]
#Add new category
murders['OtherPerCap_bins'] = pd.cut(murders['OtherPerCap'], bins=OtherPerCap_bin, labels=OtherPerCap_labels)
murders.head()

0.0
137000.0


murders['OtherPerCap_bins'].value_counts()

8000-11500      531
11500-137000    472
0-5500          469
5500-8000       447
Name: OtherPerCap_bins, dtype: int64


murders['HispPerCap'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['HispPerCap'].min())
print(murders['HispPerCap'].max())

#Determine bins based on quantiles
HispPerCap_ = pd.qcut(murders['HispPerCap'], q=4)
#Check the value counts of each bin to ensure they are balanced
HispPerCap_.value_counts()

#Create bin labels
HispPerCap_labels = ['0-7500', '7500-1000', '1000-13500', '13500-55000']
#Create bins
HispPerCap_bin = [-1, 7500, 10000, 13500, 55000]
#Add new category
murders['HispPerCap_bins'] = pd.cut(murders['HispPerCap'], bins=HispPerCap_bin, labels=HispPerCap_labels)
murders.head()

0
54648


murders['HispPerCap_bins'].value_counts()

0-7500         522
7500-1000      487
13500-55000    469
1000-13500     441
Name: HispPerCap_bins, dtype: int64


murders['PctPopUnderPov'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['PctPopUnderPov'].min())
print(murders['PctPopUnderPov'].max())

#Determine bins based on quantiles
PctPopUnderPov_ = pd.qcut(murders['PctPopUnderPov'], q=4)
#Check the value counts of each bin to ensure they are balanced
PctPopUnderPov_.value_counts()

#Create bin labels
PctPopUnderPov_labels = ['0-5%', '5-10%', '10-17%', '17-60%']
#Create bins
PctPopUnderPov_bin = [0, 5, 10, 17, 60]
#Add new category
murders['PctPopUnderPov_bins'] = pd.cut(murders['PctPopUnderPov'], bins=PctPopUnderPov_bin, labels=PctPopUnderPov_labels)
murders.head()

0.64
48.82


murders['PctPopUnderPov_bins'].value_counts()

0-5%      522
17-60%    483
5-10%     477
10-17%    437
Name: PctPopUnderPov_bins, dtype: int64


murders['PctLess9thGrade'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['PctLess9thGrade'].min())
print(murders['PctLess9thGrade'].max())

#Determine bins based on quantiles
PctLess9thGrade_ = pd.qcut(murders['PctLess9thGrade'], q=4)
#Check the value counts of each bin to ensure they are balanced
PctLess9thGrade_.value_counts()

#Create bin labels
PctLess9thGrade_labels = ['0-5%', '5-8%', '8-12%', '12-50%']
#Create bins
PctLess9thGrade_bin = [0, 5, 8, 12, 50]
#Add new category
murders['PctLess9thGrade_bins'] = pd.cut(murders['PctLess9thGrade'], bins=PctLess9thGrade_bin, labels=PctLess9thGrade_labels)
murders.head()

0.2
49.89


murders['PctLess9thGrade_bins'].value_counts()

0-5%      516
12-50%    488
5-8%      462
8-12%     453
Name: PctLess9thGrade_bins, dtype: int64


murders['PctBSorMore'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['PctBSorMore'].min())
print(murders['PctBSorMore'].max())

#Determine bins based on quantiles
PctBSorMore_ = pd.qcut(murders['PctBSorMore'], q=4)
#Check the value counts of each bin to ensure they are balanced
PctBSorMore_.value_counts()

#Create bin labels
PctBSorMore_labels = ['0-14', '14-19', '19-30', '30-80']
#Create bins
PctBSorMore_bin = [0, 14, 19, 30, 80]
#Add new category
murders['PctBSorMore_bins'] = pd.cut(murders['PctBSorMore'], bins=PctBSorMore_bin, labels=PctBSorMore_labels)
murders.head()

1.63
73.63


murders['PctBSorMore_bins'].value_counts()

19-30    565
0-14     473
14-19    443
30-80    438
Name: PctBSorMore_bins, dtype: int64


murders['PctEmplManu'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


# apply normalization technique, using a range of [0,1]
murders['PctEmplManu_norm'] = (murders['PctEmplManu'] - murders['PctEmplManu'].min()) / (murders['PctEmplManu'].max() - murders['PctEmplManu'].min())    
  
murders.head()


murders['PctEmplProfServ'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


# apply normalization technique, using a range of [0,1]
murders['PctEmplProfServ_norm'] = (murders['PctEmplProfServ'] - murders['PctEmplProfServ'].min()) / (murders['PctEmplProfServ'].max() - murders['PctEmplProfServ'].min())    
  
murders.head()


murders = murders.drop(['PctEmplProfServ_bins'], axis=1)


murders['PctOccupManu'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


# apply normalization technique, using a range of [0,1]
murders['PctOccupManu_norm'] = (murders['PctOccupManu'] - murders['PctOccupManu'].min()) / (murders['PctOccupManu'].max() - murders['PctOccupManu'].min())    
  
murders.head()


murders['MalePctDivorce'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


# apply normalization technique, using a range of [0,1]
murders['MalePctDivorce_norm'] = (murders['MalePctDivorce'] - murders['MalePctDivorce'].min()) / (murders['MalePctDivorce'].max() - murders['MalePctDivorce'].min())    
  
murders.head()


murders['MalePctNevMarr'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


# apply normalization technique, using a range of [0,1]
murders['MalePctNevMarr_norm'] = (murders['MalePctNevMarr'] - murders['MalePctNevMarr'].min()) / (murders['MalePctNevMarr'].max() - murders['MalePctNevMarr'].min())    
  
murders.head()


murders = murders.drop(['MalePctNevMarr_bins'], axis=1)


murders['PctFam2Par'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['PctFam2Par'].min())
print(murders['PctFam2Par'].max())

#Determine bins based on quantiles
PctFam2Par_ = pd.qcut(murders['PctFam2Par'], q=4)
#Check the value counts of each bin to ensure they are balanced
PctFam2Par_.value_counts()

#Create bin labels
PctFam2Par_labels = ['0-67%', '67-70%', '75-82%', '82-95%']
#Create bins
PctFam2Par_bin = [0, 67, 75, 82, 95]
#Add new category
murders['PctFam2Par_bins'] = pd.cut(murders['PctFam2Par'], bins=PctFam2Par_bin, labels=PctFam2Par_labels)
murders.head()

32.24
93.6


murders['PctFam2Par_bins'].value_counts()

67-70%    533
75-82%    482
82-95%    462
0-67%     442
Name: PctFam2Par_bins, dtype: int64


murders['PctWorkMomYoungKids'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


# apply normalization technique, using a range of [0,1]
murders['PctWorkMomYoungKids_norm'] = (murders['PctWorkMomYoungKids'] - murders['PctWorkMomYoungKids'].min()) / (murders['PctWorkMomYoungKids'].max() - murders['PctWorkMomYoungKids'].min())    
  
murders.head()


murders['PctImmigRecent'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['PctImmigRecent'].min())
print(murders['PctImmigRecent'].max())

#Determine bins based on quantiles
PctImmigRecent_ = pd.qcut(murders['PctImmigRecent'], q=4)
#Check the value counts of each bin to ensure they are balanced
PctImmigRecent_.value_counts()

#Create bin labels
PctImmigRecent_labels = ['0-7%', '7-12%', '12-18%', '18-65%']
#Create bins
PctImmigRecent_bin = [-1, 7, 12, 18, 65]
#Add new category
murders['PctImmigRecent_bins'] = pd.cut(murders['PctImmigRecent'], bins=PctImmigRecent_bin, labels=PctImmigRecent_labels)
murders.head()

0.0
64.29


murders['PctImmigRecent_bins'].value_counts()

12-18%    515
18-65%    486
0-7%      482
7-12%     436
Name: PctImmigRecent_bins, dtype: int64


murders['PctRecentImmig'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['PctRecentImmig'].min())
print(murders['PctRecentImmig'].max())

#Determine bins based on quantiles
PctRecentImmig_ = pd.qcut(murders['PctRecentImmig'], q=4)
#Check the value counts of each bin to ensure they are balanced
PctRecentImmig_.value_counts()

#Create bin labels
PctRecentImmig_labels = ['0-0.2%', '0.2-0.5%', '0.5-1.3%', '1.3-13.7%']
#Create bins
PctRecentImmig_bin = [-1, 0.2, 0.5, 1.3, 13.71]
#Add new category
murders['PctRecentImmig_bins'] = pd.cut(murders['PctRecentImmig'], bins=PctRecentImmig_bin, labels=PctRecentImmig_labels)
murders.head()

0.0
13.71


murders['PctRecentImmig_bins'].value_counts()

0-0.2%       526
1.3-13.7%    516
0.5-1.3%     474
0.2-0.5%     403
Name: PctRecentImmig_bins, dtype: int64


murders['PctPersOwnOccup'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


# apply normalization technique, using a range of [0,1]
murders['PctPersOwnOccup_norm'] = (murders['PctPersOwnOccup'] - murders['PctPersOwnOccup'].min()) / (murders['PctPersOwnOccup'].max() - murders['PctPersOwnOccup'].min())    
  
murders.head()


murders['PctHousLess3BR'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


# apply normalization technique, using a range of [0,1]
murders['PctHousLess3BR_norm'] = (murders['PctHousLess3BR'] - murders['PctHousLess3BR'].min()) / (murders['PctHousLess3BR'].max() - murders['PctHousLess3BR'].min())    
  
murders.head()


murders['MedNumBR'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['MedNumBR'].min())
print(murders['MedNumBR'].max())

#Determine bins based on quantiles
murders['MedNumBR'].describe()

#Create bin labels
MedNumBR_labels = ['0-2.5', '2.5-4']
#Create bins
MedNumBR_bin = [0, 2.5, 4]
#Add new category
murders['MedNumBR_bins'] = pd.cut(murders['MedNumBR'], bins=MedNumBR_bin, labels=MedNumBR_labels)
murders.head()

1
4


murders['MedNumBR_bins'].value_counts()

2.5-4    1176
0-2.5     743
Name: MedNumBR_bins, dtype: int64


murders['PctHousOccup'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['PctHousOccup'].min())
print(murders['PctHousOccup'].max())

#Determine bins based on quantiles
PctHousOccup_ = pd.qcut(murders['PctHousOccup'], q=4)
#Check the value counts of each bin to ensure they are balanced
PctHousOccup_.value_counts()

#Create bin labels
PctHousOccup_labels = ['30-91%', '91-94%', '94-96%', '96-99%']
#Create bins
PctHousOccup_bin = [30, 91, 94, 96, 99]
#Add new category
murders['PctHousOccup_bins'] = pd.cut(murders['PctHousOccup'], bins=PctHousOccup_bin, labels=PctHousOccup_labels)
murders.head()

37.47
99.0


murders['PctHousOccup_bins'].value_counts()

94-96%    495
30-91%    486
91-94%    475
96-99%    463
Name: PctHousOccup_bins, dtype: int64


murders['PctVacantBoarded'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['PctVacantBoarded'].min())
print(murders['PctVacantBoarded'].max())

#Determine bins based on quantiles
PctVacantBoarded_ = pd.qcut(murders['PctVacantBoarded'], q=4)
#Check the value counts of each bin to ensure they are balanced
PctVacantBoarded_.value_counts()

#Create bin labels
PctVacantBoarded_labels = ['0-0.75%', '0.75-1.75%', '1.75-4%', '4-40%']
#Create bins
PctVacantBoarded_bin = [-1, 0.75, 1.75, 4, 40]
#Add new category
murders['PctVacantBoarded_bins'] = pd.cut(murders['PctVacantBoarded'], bins=PctVacantBoarded_bin, labels=PctVacantBoarded_labels)
murders.head()

0.0
39.89


murders['PctVacantBoarded_bins'].value_counts()

1.75-4%       540
0.75-1.75%    500
0-0.75%       473
4-40%         406
Name: PctVacantBoarded_bins, dtype: int64


murders['PctVacMore6Mos'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


# apply normalization technique, using a range of [0,1]
murders['PctVacMore6Mos_norm'] = (murders['PctVacMore6Mos'] - murders['PctVacMore6Mos'].min()) / (murders['PctVacMore6Mos'].max() - murders['PctVacMore6Mos'].min())    
  
murders.head()


murders['MedYrHousBuilt'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['MedYrHousBuilt'].min())
print(murders['MedYrHousBuilt'].max())

#Determine bins based on quantiles
MedYrHousBuilt_ = pd.qcut(murders['MedYrHousBuilt'], q=4)
#Check the value counts of each bin to ensure they are balanced
MedYrHousBuilt_.value_counts()

#Create bin labels
MedYrHousBuilt_labels = ['1939-1956', '1956-1964', '1964-1971', '1971-1987']
#Create bins
MedYrHousBuilt_bin = [0, 1956, 1964, 1971, 1987]
#Add new category
murders['MedYrHousBuilt_bins'] = pd.cut(murders['MedYrHousBuilt'], bins=MedYrHousBuilt_bin, labels=MedYrHousBuilt_labels)
murders.head()

1939
1987


murders['MedYrHousBuilt_bins'].value_counts()

1956-1964    516
1939-1956    501
1964-1971    454
1971-1987    448
Name: MedYrHousBuilt_bins, dtype: int64


murders['PctWOFullPlumb'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['PctWOFullPlumb'].min())
print(murders['PctWOFullPlumb'].max())

#Determine bins based on quantiles
PctWOFullPlumb_ = pd.qcut(murders['PctWOFullPlumb'], q=4)
#Check the value counts of each bin to ensure they are balanced
PctWOFullPlumb_.value_counts()

#Create bin labels
PctWOFullPlumb_labels = ['0-0.16%', '0.16-0.3%', '0.3-0.5%', '0.5-5%']
#Create bins
PctWOFullPlumb_bin = [-1, 0.16, 0.3, 0.5, 5.33]
#Add new category
murders['PctWOFullPlumb_bins'] = pd.cut(murders['PctWOFullPlumb'], bins=PctWOFullPlumb_bin, labels=PctWOFullPlumb_labels)
murders.head()

0.0
5.33


murders['PctWOFullPlumb_bins'].value_counts()

0.5-5%       564
0.3-0.5%     475
0-0.16%      453
0.16-0.3%    427
Name: PctWOFullPlumb_bins, dtype: int64


murders['RentQrange'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['RentQrange'].min())
print(murders['RentQrange'].max())

#Determine bins based on quantiles
RentQrange_ = pd.qcut(murders['RentQrange'], q=4)
#Check the value counts of each bin to ensure they are balanced
RentQrange_.value_counts()


#Create bin labels
RentQrange_labels = ['0-140', '140-170', '170-230', '230-805']
#Create bins
RentQrange_bin = [-1, 140, 170, 230, 803]
#Add new category
murders['RentQrange_bins'] = pd.cut(murders['RentQrange'], bins=RentQrange_bin, labels=RentQrange_labels)
murders.head()

0
803


murders['RentQrange_bins'].value_counts()

230-805    534
0-140      489
170-230    482
140-170    414
Name: RentQrange_bins, dtype: int64


murders['MedRentPctHousInc'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


# apply normalization technique, using a range of [0,1]
murders['MedRentPctHousInc_norm'] = (murders['MedRentPctHousInc'] - murders['MedRentPctHousInc'].min()) / (murders['MedRentPctHousInc'].max() - murders['MedRentPctHousInc'].min())    
  
murders.head()


murders['MedOwnCostPctInc'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


# apply normalization technique, using a range of [0,1]
murders['MedOwnCostPctInc_norm'] = (murders['MedOwnCostPctInc'] - murders['MedOwnCostPctInc'].min()) / (murders['MedOwnCostPctInc'].max() - murders['MedOwnCostPctInc'].min())    
  
murders.head()


murders['MedOwnCostPctIncNoMtg'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['MedOwnCostPctIncNoMtg'].min())
print(murders['MedOwnCostPctIncNoMtg'].max())

#Determine bins based on quantiles
MedOwnCostPctIncNoMtg_ = pd.qcut(murders['MedOwnCostPctIncNoMtg'], q=4)
#Check the value counts of each bin to ensure they are balanced
MedOwnCostPctIncNoMtg_.value_counts()

#Create bin labels
MedOwnCostPctIncNoMtg_labels = ['10-12%', '12-13%', '13-14%', '14-25%']
#Create bins
MedOwnCostPctIncNoMtg_bin = [10, 12, 13, 14, 25]
#Add new category
murders['MedOwnCostPctIncNoMtg_bins'] = pd.cut(murders['MedOwnCostPctIncNoMtg'], bins=MedOwnCostPctIncNoMtg_bin, labels=MedOwnCostPctIncNoMtg_labels)
murders.head()

10.1
23.4


murders['MedOwnCostPctIncNoMtg_bins'].value_counts()

12-13%    559
10-12%    538
13-14%    434
14-25%    388
Name: MedOwnCostPctIncNoMtg_bins, dtype: int64


murders['PctBornSameState'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['PctBornSameState'].min())
print(murders['PctBornSameState'].max())

#Determine bins based on quantiles
PctBornSameState_ = pd.qcut(murders['PctBornSameState'], q=4)
#Check the value counts of each bin to ensure they are balanced
PctBornSameState_.value_counts()

#Create bin labels
PctBornSameState_labels = ['0-50%', '50-65%', '65-75%', '75-95%']
#Create bins
PctBornSameState_bin = [0, 50, 65, 75, 95]
#Add new category
murders['PctBornSameState_bins'] = pd.cut(murders['PctBornSameState'], bins=PctBornSameState_bin, labels=PctBornSameState_labels)
murders.head()

6.75
93.14


murders['PctBornSameState_bins'].value_counts()

0-50%     535
50-65%    520
65-75%    433
75-95%    431
Name: PctBornSameState_bins, dtype: int64


murders['PctSameHouse85'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


# apply normalization technique, using a range of [0,1]
murders['PctSameHouse85_norm'] = (murders['PctSameHouse85'] - murders['PctSameHouse85'].min()) / (murders['PctSameHouse85'].max() - murders['PctSameHouse85'].min())    
  
murders.head()


murders['PctSameState85'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['PctSameState85'].min())
print(murders['PctSameState85'].max())

#Determine bins based on quantiles
PctSameState85_ = pd.qcut(murders['PctSameState85'], q=4)
#Check the value counts of each bin to ensure they are balanced
PctSameState85_.value_counts()

#Create bin labels
PctSameState85_labels = ['32-85%', '85-90%', '90-93%', '93-100%']
#Create bins
PctSameState85_bin = [32, 85, 90, 93, 100]
#Add new category
murders['PctSameState85_bins'] = pd.cut(murders['PctSameState85'], bins=PctSameState85_bin, labels=PctSameState85_labels)
murders.head()

32.83
99.9


murders['PctSameState85_bins'].value_counts()

32-85%     505
85-90%     500
90-93%     473
93-100%    441
Name: PctSameState85_bins, dtype: int64


murders['LandArea'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['LandArea'].min())
print(murders['LandArea'].max())

#Determine bins based on quantiles
LandArea_ = pd.qcut(murders['LandArea'], q=4)
#Check the value counts of each bin to ensure they are balanced
LandArea_.value_counts()

#Create bin labels
LandArea_labels = ['0-7', '7-14', '14-26', '26-4000']
#Create bins
LandArea_bin = [0, 7, 14, 26, 3570]
#Add new category
murders['LandArea_bins'] = pd.cut(murders['LandArea'], bins=LandArea_bin, labels=LandArea_labels)
murders.head()

0.9
3569.8


murders['LandArea_bins'].value_counts()

7-14       525
0-7        467
26-4000    465
14-26      462
Name: LandArea_bins, dtype: int64


murders['PopDens'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['PopDens'].min())
print(murders['PopDens'].max())

#Determine bins based on quantiles
PopDens_ = pd.qcut(murders['PopDens'], q=4)
#Check the value counts of each bin to ensure they are balanced
PopDens_.value_counts()

#Create bin labels
PopDens_labels = ['10-1200', '1200-2000', '2000-3300', '3300-45000']
#Create bins
PopDens_bin = [9, 1200, 2000, 3300, 45000]
#Add new category
murders['PopDens_bins'] = pd.cut(murders['PopDens'], bins=PopDens_bin, labels=PopDens_labels)
murders.head()

10.0
44229.9


murders['PopDens_bins'].value_counts()

10-1200       496
2000-3300     488
3300-45000    478
1200-2000     457
Name: PopDens_bins, dtype: int64


murders['PctUsePubTrans'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['PctUsePubTrans'].min())
print(murders['PctUsePubTrans'].max())

#Determine bins based on quantiles
PctUsePubTrans_ = pd.qcut(murders['PctUsePubTrans'], q=4)
#Check the value counts of each bin to ensure they are balanced
PctUsePubTrans_.value_counts()

#Create bin labels
PctUsePubTrans_labels = ['0-0.4%', '0.4-1.2%', '1.2-3.3%', '3.3-55%']
#Create bins
PctUsePubTrans_bin = [-1, 0.4, 1.2, 3.3, 55]
#Add new category
murders['PctUsePubTrans_bins'] = pd.cut(murders['PctUsePubTrans'], bins=PctUsePubTrans_bin, labels=PctUsePubTrans_labels)
murders.head()

0.0
54.33


murders['PctUsePubTrans_bins'].value_counts()

0-0.4%      516
3.3-55%     495
1.2-3.3%    487
0.4-1.2%    421
Name: PctUsePubTrans_bins, dtype: int64


murders['LemasPctOfficDrugUn'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


#Check the minimum and maximum value
print(murders['LemasPctOfficDrugUn'].min())
print(murders['LemasPctOfficDrugUn'].max())

#Determine bins based on quantiles
murders['LemasPctOfficDrugUn'].describe()

#Create bin labels
PctUsePubTrans_labels = ['0%', '0.5-50%']
#Create bins
PctUsePubTrans_bin = [-1, 0.44, 60]
#Add new category
murders['PctUsePubTrans_bins'] = pd.cut(murders['PctUsePubTrans'], bins=PctUsePubTrans_bin, labels=PctUsePubTrans_labels)
murders.head()

0.0
48.44


murders['PctUsePubTrans_bins'].value_counts()

0.5-50%    1386
0%          533
Name: PctUsePubTrans_bins, dtype: int64


murders['murdPerPop'].hist(bins=50)
plt.title('Distribution')
plt.xlabel('x lable')
plt.ylabel('y lable')
plt.show()


murders_backup = murders


#Check the minimum and maximum value
print(murders['murdPerPop'].min())
print(murders['murdPerPop'].max())

#Determine bins based on quantiles
murdPerPop_ = pd.qcut(murders['murdPerPop'], q=2)
#Check the value counts of each bin to ensure they are balanced
murdPerPop_.value_counts()

#Create bin labels
murdPerPop_labels = ['No', 'Yes']
#Create bins
murdPerPop_bin = [-1, 0, 100]
#Add new category
murders['murdPerPop_class_target'] = pd.cut(murders['murdPerPop'], bins=murdPerPop_bin, labels=murdPerPop_labels)
murders.head()

0.0
91.09


murders['murdPerPop_class_target'].value_counts()

Yes    1043
No      876
Name: murdPerPop_class_target, dtype: int64


murders_classification = murders[['state','pop_bins','householdsize_norm', 'racepctblack_bins', 'racePctWhite_bins', 
                                  'racePctAsian_bins', 'racePctHisp_bins', 'agePct12t21_norm', 'agePct65up_norm', 'pctUrban_bins', 
                                  'medIncome_bins', 'pctWFarmSelf_bins', 'pctWInvInc_norm', 'pctWPubAsst_bins', 'pctWRetire_norm', 
                                  'blackPerCap_bins', 'indianPerCap_bins', 'AsianPerCap_bins', 'OtherPerCap_bins', 'HispPerCap_bins', 
                                  'PctPopUnderPov_bins', 'PctLess9thGrade_bins', 'PctBSorMore_bins','PctEmplManu_norm','PctEmplProfServ_norm',
                                  'PctOccupManu_norm','MalePctDivorce_norm','MalePctNevMarr_norm','PctFam2Par_bins','PctWorkMomYoungKids_norm',
                                  'PctImmigRecent_bins','PctRecentImmig_bins','PctPersOwnOccup_norm','PctHousLess3BR_norm','MedNumBR_bins',
                                  'PctHousOccup_bins','PctVacantBoarded_bins','PctVacMore6Mos_norm','MedYrHousBuilt_bins','PctWOFullPlumb_bins',
                                  'RentQrange_bins','MedRentPctHousInc_norm','MedOwnCostPctInc_norm','MedOwnCostPctIncNoMtg_bins',
                                  'PctBornSameState_bins','PctSameHouse85_norm','PctSameState85_bins','LandArea_bins','PopDens_bins',
                                  'PctUsePubTrans_bins', 'murdPerPop_class_target']].copy()

murders_classification.head()
murders_classification.info()


murders_class_backup = murders_classification
murders_class_backup.info()


murders_classification['state'] = murders_classification['state'].astype('category')


murders_class_backup = murders_classification


# apply normalization technique, using a range of [0,1]
murders['murdPerPop_reg_target'] = (murders['murdPerPop'] - murders['murdPerPop'].min()) / (murders['murdPerPop'].max() - murders['murdPerPop'].min())    
  
murders.head()


murders_regression = murders[['state','pop_bins','householdsize_norm', 'racepctblack_bins', 'racePctWhite_bins', 
                              'racePctAsian_bins', 'racePctHisp_bins', 'agePct12t21_norm', 'agePct65up_norm', 'pctUrban_bins', 
                              'medIncome_bins', 'pctWFarmSelf_bins', 'pctWInvInc_norm', 'pctWPubAsst_bins', 'pctWRetire_norm', 
                              'blackPerCap_bins', 'indianPerCap_bins', 'AsianPerCap_bins', 'OtherPerCap_bins', 'HispPerCap_bins', 
                              'PctPopUnderPov_bins', 'PctLess9thGrade_bins', 'PctBSorMore_bins','PctEmplManu_norm','PctEmplProfServ_norm',
                              'PctOccupManu_norm','MalePctDivorce_norm','MalePctNevMarr_norm','PctFam2Par_bins','PctWorkMomYoungKids_norm',
                              'PctImmigRecent_bins','PctRecentImmig_bins','PctPersOwnOccup_norm','PctHousLess3BR_norm','MedNumBR_bins',
                              'PctHousOccup_bins','PctVacantBoarded_bins','PctVacMore6Mos_norm','MedYrHousBuilt_bins','PctWOFullPlumb_bins',
                              'RentQrange_bins','MedRentPctHousInc_norm','MedOwnCostPctInc_norm','MedOwnCostPctIncNoMtg_bins',
                              'PctBornSameState_bins','PctSameHouse85_norm','PctSameState85_bins','LandArea_bins','PopDens_bins',
                              'PctUsePubTrans_bins', 'murdPerPop_reg_target']].copy()

murders_regression.head()


murders_reg_backup = murders_regression


murders_regression['state'] = murders_regression['state'].astype('category')


print(murders_copy.columns.difference(robberies.columns))
print(robberies.columns.difference(murders_copy.columns))

Index(['murdPerPop'], dtype='object')
Index(['robbbPerPop'], dtype='object')


murders.head()


#Create our normalized robberies dataframes

#REGRESSION DATASET
robberies_regression = murders[['state','pop_bins','householdsize_norm', 'racepctblack_bins', 'racePctWhite_bins', 
                                'racePctAsian_bins', 'racePctHisp_bins', 'agePct12t21_norm', 'agePct65up_norm', 'pctUrban_bins', 'medIncome_bins',
                                  'pctWFarmSelf_bins', 'pctWInvInc_norm', 'pctWPubAsst_bins', 'pctWRetire_norm', 'blackPerCap_bins', 
                                  'indianPerCap_bins', 'AsianPerCap_bins', 'OtherPerCap_bins', 'HispPerCap_bins', 'PctPopUnderPov_bins', 
                                  'PctLess9thGrade_bins', 'PctBSorMore_bins','PctEmplManu_norm','PctEmplProfServ_norm','PctOccupManu_norm',
                                  'MalePctDivorce_norm','MalePctNevMarr_norm','PctFam2Par_bins','PctWorkMomYoungKids_norm','PctImmigRecent_bins',
                                  'PctRecentImmig_bins','PctPersOwnOccup_norm','PctHousLess3BR_norm','MedNumBR_bins','PctHousOccup_bins',
                                  'PctVacantBoarded_bins','PctVacMore6Mos_norm','MedYrHousBuilt_bins','PctWOFullPlumb_bins','RentQrange_bins',
                                  'MedRentPctHousInc_norm','MedOwnCostPctInc_norm','MedOwnCostPctIncNoMtg_bins','PctBornSameState_bins',
                                  'PctSameHouse85_norm','PctSameState85_bins','LandArea_bins','PopDens_bins','PctUsePubTrans_bins']].copy()

robberies_regression.info()


robberies_regression['state'] = robberies_regression['state'].astype('category')


# apply normalization technique, using a range of [0,1]
robberies_regression['robbbPerPop_reg_target'] = (robberies['robbbPerPop'] - robberies['robbbPerPop'].min()) / (robberies['robbbPerPop'].max() - robberies['robbbPerPop'].min())    
  
robberies_regression.head()


#CLASSIFICATION DATASET
robberies_classification = murders[['state','pop_bins','householdsize_norm', 'racepctblack_bins', 'racePctWhite_bins', 
                                    'racePctAsian_bins', 'racePctHisp_bins', 'agePct12t21_norm', 'agePct65up_norm', 'pctUrban_bins', 
                                    'medIncome_bins', 'pctWFarmSelf_bins', 'pctWInvInc_norm', 'pctWPubAsst_bins', 'pctWRetire_norm', 
                                    'blackPerCap_bins', 'indianPerCap_bins', 'AsianPerCap_bins', 'OtherPerCap_bins', 'HispPerCap_bins', 
                                    'PctPopUnderPov_bins', 'PctLess9thGrade_bins', 'PctBSorMore_bins','PctEmplManu_norm','PctEmplProfServ_norm',
                                    'PctOccupManu_norm','MalePctDivorce_norm','MalePctNevMarr_norm','PctFam2Par_bins','PctWorkMomYoungKids_norm',
                                    'PctImmigRecent_bins','PctRecentImmig_bins','PctPersOwnOccup_norm','PctHousLess3BR_norm','MedNumBR_bins',
                                    'PctHousOccup_bins','PctVacantBoarded_bins','PctVacMore6Mos_norm','MedYrHousBuilt_bins','PctWOFullPlumb_bins',
                                    'RentQrange_bins','MedRentPctHousInc_norm','MedOwnCostPctInc_norm','MedOwnCostPctIncNoMtg_bins',
                                    'PctBornSameState_bins','PctSameHouse85_norm','PctSameState85_bins','LandArea_bins','PopDens_bins',
                                    'PctUsePubTrans_bins']].copy()

robberies_classification.info()


robberies_classification['state']=robberies_classification['state'].astype('category')


#Check the minimum and maximum value
print(robberies['robbbPerPop'].min())
print(robberies['robbbPerPop'].max())

#Determine bins based on quantiles
robbbPerPop_ = pd.qcut(robberies['robbbPerPop'], q=3)
#Check the value counts of each bin to ensure they are balanced
robbbPerPop_.value_counts()

#Create bin labels
robbbPerPop_labels = ['Unlikely', 'Likely', 'Very Likely']
#Create bins
robbbPerPop_bin = [-1, 40, 145, 2500]
#Add new category
robberies_classification['robbbPerPop_class_target'] = pd.cut(robberies['robbbPerPop'], bins=robbbPerPop_bin, labels=robbbPerPop_labels)
robberies_classification.head()

0.0
2264.13


robberies_classification['robbbPerPop_class_target'].value_counts()

Likely         656
Very Likely    642
Unlikely       621
Name: robbbPerPop_class_target, dtype: int64


#MAKING COPIES OF ALL DATASETS FOR BACKUP

murd_reg_copy = murders_regression.copy()
rob_reg_copy = robberies_regression.copy()

murders_class_copy = murders_classification.copy()
rob_class_copy = robberies_classification.copy()

murders_reg_backup = murders_regression
robberies_reg_backup = robberies_regression

murdregcopy = murders_regression.copy()


#Make a backup copy of our dataset
murdclasscopy = murders_class_copy


#Encode the cateogorical variables with LABEL ENCODING METHOD
#This code block is a test run, encoding the column 'state'
#If successful, the rest of the categorical variables will be encoded the same way

from sklearn.preprocessing import LabelEncoder

#create instance of label encoder
lab = LabelEncoder()

#perform label encoding on 'team' column
murdclasscopy['state'] = lab.fit_transform(murdclasscopy['state'])


#Encode the rest of the categorical variables with for loop function

for cols in murdclasscopy.columns:
    if murdclasscopy[cols].dtype == 'category':
        murdclasscopy[cols] = lab.fit_transform(murdclasscopy[cols])
    else:
       pass
murdclasscopy.head()


#check info of our dataframe to ensure it is of the correct type, and that all of the categorical attributes were transformed

murdclasscopy.info()


#Split the data into train test split
from sklearn.model_selection import train_test_split

#Split the dataset into training set and test set
#Our class column is murdPerPop_class_target, everything else will be used as features
class_murd_colname = 'murdPerPop_class_target'
feature_murd_names = murdclasscopy.columns[murdclasscopy.columns != class_murd_colname]

#70% training and 30% test
x1_train, x1_test, y1_train, y1_test = train_test_split(murdclasscopy.loc[:, feature_murd_names], 
                                                    murdclasscopy[class_murd_colname], test_size=0.3, random_state=42)


#LOGISTIC REGRESSION

from sklearn.linear_model import LogisticRegression

logmodel = LogisticRegression(class_weight= 'balanced')
logmodel.fit(x1_train, y1_train)
predictions_log = logmodel.predict(x1_test)

predictions_log


#KNN ALGORITHM

from sklearn.neighbors import KNeighborsClassifier 
 
classifier = KNeighborsClassifier(n_neighbors=5) 
classifier.fit(x1_train, y1_train) 

murd_pred = classifier.predict(x1_test)  
murd_pred


#DECISION TREE

from matplotlib import pyplot as plt
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree

#create and train the model

clf = DecisionTreeClassifier(max_depth=5, random_state=1234)
model = clf.fit(x1_train, y1_train)

#Predict the response for test dataset
murd_treepred = clf.predict(x1_test)
murd_treepred


from sklearn.tree import plot_tree

#plot tree (visual representation)

features = feature_murd_names
classes = class_murd_colname

plt.figure(figsize=(40, 40))
plot_tree(clf,
          fontsize=10,
          feature_names=features,
          class_names=classes,
          rounded=True,
          filled=True,
          proportion=True);


#plot tree (textual representation)

text_representation = tree.export_text(clf)
print(text_representation)


#RANDOM FOREST
from sklearn.ensemble import RandomForestClassifier

randf=RandomForestClassifier()
randf.fit(x1_train, y1_train)

murd_rf_pred = randf.predict(x1_test)
murd_rf_pred


#CONFUSION MATRICES

from sklearn.metrics import confusion_matrix
log_cm = confusion_matrix(y1_test, predictions_log)
knn_cm = confusion_matrix(y1_test, murd_pred)
dt_cm = confusion_matrix(y1_test, murd_treepred)
rf_cm = confusion_matrix(y1_test, murd_rf_pred)

print('LOGISTIC REGRESSION CONFUSION MATRIX')
print(log_cm)
print('KNN CONFUSION MATRIX')
print(knn_cm)
print('DECISION TREE CONFUSION MATRIX')
print(dt_cm)
print('RANDOM FOREST CONFUSION MATRIX')
print(rf_cm)

LOGISTIC REGRESSION CONFUSION MATRIX
[[206  53]
 [ 73 244]]
KNN CONFUSION MATRIX
[[183  76]
 [ 72 245]]
DECISION TREE CONFUSION MATRIX
[[197  62]
 [ 74 243]]
RANDOM FOREST CONFUSION MATRIX
[[195  64]
 [ 74 243]]


#EVALUATION METRICS

log_accuracy = (log_cm[0][0] + log_cm[1][1])/(len(y1_test))
log_precision = log_cm[0][0]/(log_cm[1][0] + log_cm[0][0])
log_recall = (log_cm[0][0]/(log_cm[0][0] + log_cm[0][1]))

knn_accuracy = (knn_cm[0][0] + knn_cm[1][1])/(len(y1_test))
knn_precision = knn_cm[0][0]/(knn_cm[1][0] + knn_cm[0][0])
knn_recall = (knn_cm[0][0]/(knn_cm[0][0] + knn_cm[0][1]))

dt_accuracy = (dt_cm[0][0] + dt_cm[1][1])/(len(y1_test))
dt_precision = dt_cm[0][0]/(dt_cm[1][0] + dt_cm[0][0])
dt_recall = (dt_cm[0][0]/(dt_cm[0][0] + dt_cm[0][1]))

rf_accuracy = (rf_cm[0][0] + rf_cm[1][1])/(len(y1_test))
rf_precision = rf_cm[0][0]/(rf_cm[1][0] + rf_cm[0][0])
rf_recall = (rf_cm[0][0]/(rf_cm[0][0] + rf_cm[0][1]))

print('ACCURACY')
print('Logistic Regression: ACCURACY=', log_accuracy)
print('KNN Classifier: ACCURACY=', knn_accuracy)
print('Decision Tree: ACCURACY=', dt_accuracy)
print('Random Forest: ACCURACY=', rf_accuracy)

print('PRECISION')
print('Logistic Regression: PRECISION=', log_precision)
print('KNN Classifier: PRECISION=', knn_precision)
print('Decision Tree: PRECISION=', dt_precision)
print('Random Forest: PRECISION=', rf_accuracy)

print('RECALL')
print('Logistic Regression: RECALL=', log_recall)
print('KNN Classifier: RECALL=', knn_recall)
print('Decision Tree: RECALL=', dt_recall)
print('Random Forest: RECALL=', rf_accuracy)

ACCURACY
Logistic Regression: ACCURACY= 0.78125
KNN Classifier: ACCURACY= 0.7430555555555556
Decision Tree: ACCURACY= 0.7638888888888888
Random Forest: ACCURACY= 0.7604166666666666
PRECISION
Logistic Regression: PRECISION= 0.7383512544802867
KNN Classifier: PRECISION= 0.7176470588235294
Decision Tree: PRECISION= 0.7269372693726938
Random Forest: PRECISION= 0.7604166666666666
RECALL
Logistic Regression: RECALL= 0.7953667953667953
KNN Classifier: RECALL= 0.7065637065637066
Decision Tree: RECALL= 0.7606177606177607
Random Forest: RECALL= 0.7604166666666666


# define dataset
X, y = murdclasscopy.loc[:, feature_murd_names], murdclasscopy[class_murd_colname]
# summarize the dataset
print(X.shape, y.shape)

(1919, 50) (1919,)


from numpy import mean
from numpy import std
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression

# prepare the cross-validation procedure
cv = KFold(n_splits=10, random_state=42, shuffle=True)


# evaluate a logistic regression model using k-fold cross-validation

# create model
log_model = LogisticRegression()
# evaluate model
log_scores_acc = cross_val_score(log_model, X, y, scoring='accuracy', cv=cv, n_jobs=-1)
log_scores_pre = cross_val_score(log_model, X, y, scoring='precision', cv=cv, n_jobs=-1)
log_scores_re = cross_val_score(log_model, X, y, scoring='recall', cv=cv, n_jobs=-1)
# report performance
print('Accuracy: %.3f (%.3f)' % (mean(log_scores_acc), std(log_scores_acc)))
print('Precision: %.3f (%.3f)' % (mean(log_scores_pre), std(log_scores_pre)))
print('Recall: %.3f (%.3f)' % (mean(log_scores_re), std(log_scores_re)))

Accuracy: 0.776 (0.029)
Precision: 0.785 (0.033)
Recall: 0.806 (0.040)


# evaluate a knn model using k-fold cross-validation

# create model
knn_model = KNeighborsClassifier()
# evaluate model
knn_scores_acc = cross_val_score(knn_model, X, y, scoring='accuracy', cv=cv, n_jobs=-1)
knn_scores_pre = cross_val_score(knn_model, X, y, scoring='precision', cv=cv, n_jobs=-1)
knn_scores_re = cross_val_score(knn_model, X, y, scoring='recall', cv=cv, n_jobs=-1)
# report performance
print('Accuracy: %.3f (%.3f)' % (mean(knn_scores_acc), std(knn_scores_acc)))
print('Precision: %.3f (%.3f)' % (mean(knn_scores_pre), std(knn_scores_pre)))
print('Recall: %.3f (%.3f)' % (mean(knn_scores_re), std(knn_scores_re)))

Accuracy: 0.752 (0.028)
Precision: 0.759 (0.030)
Recall: 0.795 (0.036)


# evaluate a decision tree model using k-fold cross-validation

# create model
dt_model = DecisionTreeClassifier(max_depth=5)
# evaluate model
dt_scores_acc = cross_val_score(dt_model, X, y, scoring='accuracy', cv=cv, n_jobs=-1)
dt_scores_pre = cross_val_score(dt_model, X, y, scoring='precision', cv=cv, n_jobs=-1)
dt_scores_re = cross_val_score(dt_model, X, y, scoring='recall', cv=cv, n_jobs=-1)
# report performance
print('Accuracy: %.3f (%.3f)' % (mean(dt_scores_acc), std(dt_scores_acc)))
print('Precision: %.3f (%.3f)' % (mean(dt_scores_pre), std(dt_scores_pre)))
print('Recall: %.3f (%.3f)' % (mean(dt_scores_re), std(dt_scores_re)))

Accuracy: 0.727 (0.029)
Precision: 0.767 (0.042)
Recall: 0.713 (0.040)


# evaluate a random forest model using k-fold cross-validation

# create model
rf_model = RandomForestClassifier()
# evaluate model
rf_scores_acc = cross_val_score(rf_model, X, y, scoring='accuracy', cv=cv, n_jobs=-1)
rf_scores_pre = cross_val_score(rf_model, X, y, scoring='precision', cv=cv, n_jobs=-1)
rf_scores_re = cross_val_score(rf_model, X, y, scoring='recall', cv=cv, n_jobs=-1)
# report performance
print('Accuracy: %.3f (%.3f)' % (mean(rf_scores_acc), std(rf_scores_acc)))
print('Precision: %.3f (%.3f)' % (mean(rf_scores_pre), std(rf_scores_pre)))
print('Recall: %.3f (%.3f)' % (mean(rf_scores_re), std(rf_scores_re)))

Accuracy: 0.768 (0.028)
Precision: 0.794 (0.030)
Recall: 0.786 (0.032)


#Create a copy of the dataset

robclasscopy = rob_class_copy.copy()
robclasscopy.head()


#Encode the cateogorical variables with LABEL ENCODING METHOD
#This code block is a test run, encoding the column 'state'
#If successful, the rest of the categorical variables will be encoded the same way

#perform label encoding on 'team' column
robclasscopy['state'] = lab.fit_transform(robclasscopy['state'])

robclasscopy.head(3)


#Encode the rest of the categorical variables with for loop function

for r_cols in robclasscopy.columns:
    if robclasscopy[r_cols].dtype == 'category':
        robclasscopy[r_cols] = lab.fit_transform(robclasscopy[r_cols])
    else:
       pass
robclasscopy.head()


#check info of our dataframe to ensure it is of the correct type, and that all of the categorical attributes were transformed

robclasscopy.info()


#Split the data into train test split
from sklearn.model_selection import train_test_split

#Split the dataset into training set and test set
#Our class column is murdPerPop_class_target, everything else will be used as features
class_rob_colname = 'robbbPerPop_class_target'
feature_rob_names = robclasscopy.columns[robclasscopy.columns != class_rob_colname]

#70% training and 30% test
x2_train, x2_test, y2_train, y2_test = train_test_split(robclasscopy.loc[:, feature_rob_names], 
                                                    robclasscopy[class_rob_colname], test_size=0.3, random_state=42)


#LOGISTIC REGRESSION

from sklearn.linear_model import LogisticRegression

rob_logmodel = LogisticRegression(class_weight= 'balanced')
logmodel.fit(x2_train, y2_train)
rob_pred_log = logmodel.predict(x2_test)

rob_pred_log


#KNN ALGORITHM

from sklearn.neighbors import KNeighborsClassifier 
 
rob_classifier = KNeighborsClassifier(n_neighbors=5) 
classifier.fit(x2_train, y2_train) 

rob_pred = classifier.predict(x2_test)  
rob_pred


#DECISION TREE

from matplotlib import pyplot as plt
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree

#create and train the model

r_clf = DecisionTreeClassifier(max_depth=5, random_state=1234)
r_model = r_clf.fit(x2_train, y2_train)

#Predict the response for test dataset
rob_treepred = r_clf.predict(x2_test)
rob_treepred


from sklearn.tree import plot_tree

#plot tree (visual representation)

r_features = feature_rob_names
r_classes = class_rob_colname

plt.figure(figsize=(40, 40))
plot_tree(r_clf,
          fontsize=10,
          feature_names=r_features,
          class_names=r_classes,
          rounded=True,
          filled=True,
          proportion=True);


#plot tree (textual representation)

text_representation = tree.export_text(r_clf)
print(text_representation)


#RANDOM FOREST
from sklearn.ensemble import RandomForestClassifier

r_randf=RandomForestClassifier()
r_randf.fit(x2_train, y2_train)

rob_rf_pred = r_randf.predict(x1_test)
rob_rf_pred


#CONFUSION MATRICES

rlog_cm = confusion_matrix(y2_test, rob_pred_log)
rknn_cm = confusion_matrix(y2_test, rob_pred)
rdt_cm = confusion_matrix(y2_test, rob_treepred)
rrf_cm = confusion_matrix(y2_test, rob_rf_pred)

print('LOGISTIC REGRESSION CONFUSION MATRIX')
print(rlog_cm)
print('KNN CONFUSION MATRIX')
print(rknn_cm)
print('DECISION TREE CONFUSION MATRIX')
print(rdt_cm)
print('RANDOM FOREST CONFUSION MATRIX')
print(rrf_cm)

LOGISTIC REGRESSION CONFUSION MATRIX
[[112  52  34]
 [ 43 141   3]
 [ 31   4 156]]
KNN CONFUSION MATRIX
[[100  56  42]
 [ 55 125   7]
 [ 37   6 148]]
DECISION TREE CONFUSION MATRIX
[[120  43  35]
 [ 64 119   4]
 [ 32   5 154]]
RANDOM FOREST CONFUSION MATRIX
[[127  41  30]
 [ 39 147   1]
 [ 27   2 162]]


#EVALUATION METRICS
from sklearn import metrics

rlog_accuracy = (metrics.accuracy_score(y2_test, rob_pred_log))
rlog_precision = (metrics.precision_score(y2_test, rob_pred_log, average='macro'))
rlog_recall = (metrics.recall_score(y2_test, rob_pred_log, average='macro'))

rknn_accuracy = (metrics.accuracy_score(y2_test, rob_pred))
rknn_precision = (metrics.precision_score(y2_test, rob_pred, average='macro'))
rknn_recall = (metrics.recall_score(y2_test, rob_pred, average='macro'))

rdt_accuracy = (metrics.accuracy_score(y2_test, rob_treepred))
rdt_precision = (metrics.precision_score(y2_test, rob_treepred, average='macro'))
rdt_recall = (metrics.recall_score(y2_test, rob_treepred, average='macro'))


rrf_accuracy = (metrics.accuracy_score(y2_test, rob_rf_pred))
rrf_precision = (metrics.precision_score(y2_test, rob_rf_pred, average='macro'))
rrf_recall = (metrics.recall_score(y2_test, rob_rf_pred, average='macro'))

print('ACCURACY')
print('Logistic Regression: ACCURACY=', rlog_accuracy)
print('KNN Classifier: ACCURACY=', rknn_accuracy)
print('Decision Tree: ACCURACY=', rdt_accuracy)
print('Random Forest: ACCURACY=', rrf_accuracy)

print('PRECISION')
print('Logistic Regression: PRECISION=', rlog_precision)
print('KNN Classifier: PRECISION=', rknn_precision)
print('Decision Tree: PRECISION=', rdt_precision)
print('Random Forest: PRECISION=', rrf_accuracy)

print('RECALL')
print('Logistic Regression: RECALL=', rlog_recall)
print('KNN Classifier: RECALL=', rknn_recall)
print('Decision Tree: RECALL=', rdt_recall)
print('Random Forest: RECALL=', rrf_accuracy)

ACCURACY
Logistic Regression: ACCURACY= 0.7100694444444444
KNN Classifier: ACCURACY= 0.6475694444444444
Decision Tree: ACCURACY= 0.6822916666666666
Random Forest: ACCURACY= 0.7569444444444444
PRECISION
Logistic Regression: PRECISION= 0.7087255778946533
KNN Classifier: PRECISION= 0.6468505222424303
Decision Tree: PRECISION= 0.688685955664951
Random Forest: PRECISION= 0.7569444444444444
RECALL
Logistic Regression: RECALL= 0.7121403958484341
KNN Classifier: RECALL= 0.6494562709530373
Decision Tree: RECALL= 0.6829023216457771
Random Forest: RECALL= 0.7569444444444444


# define dataset
X1, y1 = robclasscopy.loc[:, feature_rob_names], robclasscopy[class_rob_colname]
# summarize the dataset
print(X1.shape, y1.shape)

(1919, 50) (1919,)


# evaluate a logistic regression model using k-fold cross-validation

# prepare the cross-validation procedure
cv = KFold(n_splits=10, random_state=42, shuffle=True)
# create model
log_model = LogisticRegression()
# evaluate model
rlog_scores_acc = cross_val_score(log_model, X1, y1, scoring='accuracy', cv=cv, n_jobs=-1)
rlog_scores_pre = cross_val_score(log_model, X1, y1, scoring='precision', cv=cv, n_jobs=-1)
rlog_scores_re = cross_val_score(log_model, X1, y1, scoring='recall', cv=cv, n_jobs=-1)
# report performance
print('Accuracy: %.3f (%.3f)' % (mean(rlog_scores_acc), std(rlog_scores_acc)))
print('Precision:',(metrics.precision_score(y2_test, rob_pred_log, average = 'macro')))
print('Recall:',(metrics.recall_score(y2_test, rob_pred_log, average = 'macro')))

Accuracy: 0.705 (0.042)
Precision: 0.7087255778946533
Recall: 0.7121403958484341


# evaluate a knn model using k-fold cross-validation

# create model
knn_model = KNeighborsClassifier()
# evaluate model
rknn_scores_acc = cross_val_score(knn_model, X1, y1, scoring='accuracy', cv=cv, n_jobs=-1)
rknn_scores_pre = cross_val_score(knn_model, X1, y1, scoring='precision', cv=cv, n_jobs=-1)
rknn_scores_re = cross_val_score(knn_model, X1, y1, scoring='recall', cv=cv, n_jobs=-1)
# report performance
print('Accuracy: %.3f (%.3f)' % (mean(rknn_scores_acc), std(rknn_scores_acc)))
print('Precision:',(metrics.precision_score(y2_test, rob_pred, average = 'macro')))
print('Recall:',(metrics.recall_score(y2_test, rob_pred, average = 'macro')))

Accuracy: 0.646 (0.031)
Precision: 0.6468505222424303
Recall: 0.6494562709530373


# evaluate a decision tree model using k-fold cross-validation

# create model
dt_model = DecisionTreeClassifier(max_depth=5)
# evaluate model
rdt_scores_acc = cross_val_score(dt_model, X1, y1, scoring='accuracy', cv=cv, n_jobs=-1)
rdt_scores_pre = cross_val_score(dt_model, X1, y1, scoring='precision', cv=cv, n_jobs=-1)
rdt_scores_re = cross_val_score(dt_model, X1, y1, scoring='recall', cv=cv, n_jobs=-1)
# report performance
print('Accuracy: %.3f (%.3f)' % (mean(rdt_scores_acc), std(rdt_scores_acc)))
print('Precision:',(metrics.precision_score(y2_test, rob_treepred, average = 'macro')))
print('Recall:', (metrics.recall_score(y2_test, rob_treepred, average = 'macro')))

Accuracy: 0.663 (0.027)
Precision: 0.688685955664951
Recall: 0.6829023216457771


# evaluate a random forest model using k-fold cross-validation

# create model
rf_model = RandomForestClassifier()
# evaluate model
rrf_scores_acc = cross_val_score(rf_model, X1, y1, scoring='accuracy', cv=cv, n_jobs=-1)
rrf_scores_pre = cross_val_score(rf_model, X1, y1, scoring='precision', cv=cv, n_jobs=-1)
rrf_scores_re = cross_val_score(rf_model, X1, y1, scoring='recall', cv=cv, n_jobs=-1)
# report performance
print('Accuracy: %.3f (%.3f)' % (mean(rrf_scores_acc),std(rdt_scores_acc)))
print('Precision:',(metrics.precision_score(y2_test, rob_rf_pred, average = 'macro')))
print('Recall:', (metrics.recall_score(y2_test, rob_rf_pred, average = 'macro')))

Accuracy: 0.714 (0.026)
Precision: 0.7570311789837287
Recall: 0.7585593124552164

	communityname	state	countyCode	communityCode	fold	population	householdsize	racepctblack	racePctWhite	racePctAsian	racePctHisp	agePct12t21	agePct12t29	agePct16t24	agePct65up	numbUrban	pctUrban	medIncome	pctWWage	pctWFarmSelf	pctWInvInc	pctWSocSec	pctWPubAsst	pctWRetire	medFamInc	perCapInc	whitePerCap	blackPerCap	indianPerCap	AsianPerCap	OtherPerCap	HispPerCap	NumUnderPov	PctPopUnderPov	PctLess9thGrade	PctNotHSGrad	PctBSorMore	PctUnemployed	PctEmploy	PctEmplManu	PctEmplProfServ	PctOccupManu	PctOccupMgmtProf	MalePctDivorce	MalePctNevMarr	FemalePctDiv	TotalPctDiv	PersPerFam	PctFam2Par	PctKids2Par	PctYoungKids2Par	PctTeen2Par	PctWorkMomYoungKids	PctWorkMom	NumKidsBornNeverMar	PctKidsBornNeverMar	NumImmig	PctImmigRecent	PctImmigRec5	PctImmigRec8	PctImmigRec10	PctRecentImmig	PctRecImmig5	PctRecImmig8	PctRecImmig10	PctSpeakEnglOnly	PctNotSpeakEnglWell	PctLargHouseFam	PctLargHouseOccup	PersPerOccupHous	PersPerOwnOccHous	PersPerRentOccHous	PctPersOwnOccup	PctPersDenseHous	PctHousLess3BR	MedNumBR	HousVacant	PctHousOccup	PctHousOwnOcc	PctVacantBoarded	PctVacMore6Mos	MedYrHousBuilt	PctHousNoPhone	PctWOFullPlumb	OwnOccLowQuart	OwnOccMedVal	OwnOccHiQuart	OwnOccQrange	RentLowQ	RentMedian	RentHighQ	RentQrange	MedRent	MedRentPctHousInc	MedOwnCostPctInc	MedOwnCostPctIncNoMtg	NumInShelters	NumStreet	PctForeignBorn	PctBornSameState	PctSameHouse85	PctSameCity85	PctSameState85	LemasSwornFT	LemasSwFTPerPop	LemasSwFTFieldOps	LemasSwFTFieldPerPop	LemasTotalReq	LemasTotReqPerPop	PolicReqPerOffic	PolicPerPop	RacialMatchCommPol	PctPolicWhite	PctPolicBlack	PctPolicHisp	PctPolicAsian	PctPolicMinor	OfficAssgnDrugUnits	NumKindsDrugsSeiz	PolicAveOTWorked	LandArea	PopDens	PctUsePubTrans	PolicCars	PolicOperBudg	LemasPctPolicOnPatr	LemasGangUnitDeploy	LemasPctOfficDrugUn	PolicBudgPerPop	murders	murdPerPop	rapes	rapesPerPop	robberies	robbbPerPop	assaults	assaultPerPop	burglaries	burglPerPop	larcenies	larcPerPop	autoTheft	autoTheftPerPop	arsons	arsonsPerPop	ViolentCrimesPerPop	nonViolPerPop
0	BerkeleyHeightstownship	NJ	39	5320	1	11980	3.10	1.37	91.78	6.50	1.88	12.47	21.44	10.93	11.33	11980	100.0	75122	89.24	1.55	70.20	23.62	1.03	18.39	79584	29711	30233	13600	5725	27101	5115	22838	227	1.96	5.81	9.90	48.18	2.70	64.55	14.65	28.82	5.49	50.73	3.67	26.38	5.22	4.47	3.22	91.43	90.17	95.78	95.81	44.56	58.88	31	0.36	1277	8.69	13.00	20.99	30.93	0.93	1.39	2.24	3.30	85.68	1.37	4.81	4.17	2.99	3.00	2.84	91.46	0.39	11.06	3	64	98.37	91.01	3.12	37.50	1959	0.00	0.28	215900	262600	326900	111000	685	1001	1001	316	1001	23.8	21.1	14.0	11	0	10.66	53.72	65.29	78.09	89.14	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	6.5	1845.9	9.63	?	?	?	?	0.00	?	0	0.00	0	0	1	8.2	4	32.81	14	114.85	138	1132.08	16	131.26	2	16.41	41.02	1394.59
1	Marpletownship	PA	45	47616	1	23123	2.82	0.80	95.57	3.44	0.85	11.01	21.30	10.48	17.18	23123	100.0	47917	78.99	1.11	64.11	35.50	2.75	22.85	55323	20148	20191	18137	0	20074	5250	12222	885	3.98	5.61	13.72	29.89	2.43	61.96	12.26	29.28	6.39	37.64	4.23	27.99	6.45	5.42	3.11	86.91	85.33	96.82	86.46	51.14	62.43	43	0.24	1920	5.21	8.65	13.33	22.50	0.43	0.72	1.11	1.87	87.79	1.81	4.25	3.34	2.70	2.83	1.96	89.03	1.01	23.60	3	240	97.15	84.88	0.00	18.33	1958	0.31	0.14	136300	164200	199900	63600	467	560	672	205	627	27.6	20.7	12.5	0	0	8.30	77.17	71.27	90.22	96.12	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	10.6	2186.7	3.84	?	?	?	?	0.00	?	0	0.00	1	4.25	5	21.26	24	102.05	57	242.37	376	1598.78	26	110.55	1	4.25	127.56	1955.95
2	Tigardcity	OR	?	?	1	29344	2.43	0.74	94.33	3.43	2.35	11.36	25.88	11.01	10.28	29344	100.0	35669	82.00	1.15	55.73	22.25	2.94	14.56	42112	16946	17103	16644	21606	15528	5954	8405	1389	4.75	2.80	9.09	30.13	4.01	69.80	15.95	21.52	8.79	32.48	10.10	25.78	14.76	12.55	2.95	78.54	78.85	92.37	75.72	66.08	74.19	164	0.88	1468	16.42	23.98	32.08	35.63	0.82	1.20	1.61	1.78	93.11	1.14	2.97	2.05	2.42	2.69	2.06	64.18	2.03	47.46	3	544	95.68	57.79	0.92	7.54	1976	1.55	0.12	74700	90400	112000	37300	370	428	520	150	484	24.1	21.7	11.6	16	0	5.00	44.77	36.60	61.26	82.85	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	10.6	2780.9	4.37	?	?	?	?	0.00	?	3	8.30	6	16.6	56	154.95	14	38.74	274	758.14	1797	4972.19	136	376.3	22	60.87	218.59	6167.51
3	Gloversvillecity	NY	35	29443	1	16656	2.40	1.70	97.35	0.50	0.70	12.55	25.20	12.19	17.57	0	0.0	20580	68.15	0.24	38.95	39.48	11.71	18.33	26501	10810	10909	9984	4941	3541	2451	4391	2831	17.23	11.05	33.68	10.81	9.86	54.74	31.22	27.43	26.76	22.71	10.98	28.15	14.47	12.91	2.98	64.02	62.36	65.38	67.43	59.59	70.27	561	3.84	339	13.86	13.86	15.34	15.34	0.28	0.28	0.31	0.31	94.98	0.56	3.93	2.56	2.37	2.51	2.20	58.18	1.21	45.66	3	669	91.19	54.89	2.54	57.85	1939	7.00	0.87	36400	49600	66500	30100	195	250	309	114	333	28.7	20.6	14.5	0	0	2.04	88.71	56.70	90.17	96.24	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	5.2	3217.7	3.31	?	?	?	?	0.00	?	0	0.00	10	57.86	10	57.86	33	190.93	225	1301.78	716	4142.56	47	271.93	?	?	306.64	?
4	Bemidjicity	MN	7	5068	1	11245	2.76	0.53	89.16	1.17	0.52	24.46	40.53	28.69	12.65	0	0.0	17390	69.33	0.55	42.82	32.16	11.21	14.43	24018	8483	9009	887	4425	3352	3000	1328	2855	29.99	12.15	23.06	25.28	9.08	52.44	6.89	36.54	10.94	27.80	7.51	50.66	11.64	9.73	2.98	58.59	55.20	66.51	79.17	61.22	68.94	402	4.70	196	46.94	56.12	67.86	69.90	0.82	0.98	1.18	1.22	94.64	0.39	5.23	3.11	2.35	2.55	2.12	58.13	2.94	55.64	2	333	92.45	53.57	3.90	42.64	1958	7.45	0.82	30600	43200	59500	28900	202	283	362	160	332	32.2	23.2	12.9	2	0	1.74	73.75	42.22	60.34	89.02	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	11.5	974.2	0.38	?	?	?	?	0.00	?	0	0.00	?	?	4	32.04	14	112.14	91	728.93	1060	8490.87	91	728.93	5	40.05	?	9988.79
5	Springfieldcity	MO	?	?	1	140494	2.45	2.51	95.65	0.90	0.95	18.09	32.89	20.04	13.26	140494	100.0	21577	75.78	1.00	41.15	29.31	7.12	14.09	27705	11878	12029	7382	10264	10753	7192	8104	23223	17.78	8.76	23.03	20.66	5.72	59.02	14.31	26.83	14.72	23.42	11.40	33.32	14.46	13.04	2.89	71.94	69.79	79.76	75.33	62.96	70.52	1511	1.58	2091	21.33	30.56	38.02	45.48	0.32	0.45	0.57	0.68	96.87	0.60	3.08	1.92	2.28	2.37	2.16	57.81	2.11	53.19	2	5119	91.81	55.50	2.09	26.22	1966	6.13	0.31	37700	53900	73100	35400	215	280	349	134	340	26.4	17.3	11.7	327	4	1.49	64.35	42.29	70.61	85.66	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	70.4	1995.7	0.97	?	?	?	?	0.00	?	7	4.63	77	50.98	136	90.05	449	297.29	2094	1386.46	7690	5091.64	454	300.6	134	88.72	442.95	6867.42
6	Norwoodtown	MA	21	50250	1	28700	2.60	1.60	96.57	1.47	1.10	11.17	27.41	12.76	14.42	28700	100.0	42805	79.47	0.39	47.70	30.23	5.41	17.23	50394	18193	18276	17342	21482	12639	21852	22594	1126	4.01	4.49	13.89	27.01	4.85	65.42	14.02	27.17	8.50	32.78	5.97	36.05	9.06	7.64	3.14	79.53	79.76	92.05	77.12	65.16	72.81	263	1.18	2637	11.38	16.27	23.93	27.76	1.05	1.49	2.20	2.55	89.98	0.60	5.08	3.46	2.55	2.89	2.09	64.62	1.47	47.35	3	566	95.11	56.96	1.41	34.45	1956	0.69	0.28	155100	179000	215500	60400	463	669	824	361	736	24.4	20.8	12.5	0	0	9.19	77.30	63.45	82.23	93.53	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	10.9	2643.5	9.62	?	?	?	?	0.00	?	0	0.00	4	13.53	9	30.44	54	182.66	110	372.09	288	974.19	144	487.1	17	57.5	226.63	1890.88
7	Andersoncity	IN	?	?	1	59459	2.45	14.20	84.87	0.40	0.63	15.31	27.93	14.78	14.60	59449	100.0	23221	71.60	0.67	35.74	32.58	8.81	22.59	28901	12161	12599	9820	6634	8802	7428	6187	10320	17.98	10.09	28.67	12.00	8.19	56.59	27.00	21.54	21.92	18.02	13.28	28.34	16.33	14.94	2.95	62.56	58.70	69.89	62.76	63.08	72.44	2368	4.66	517	13.15	22.82	28.24	33.08	0.11	0.20	0.25	0.29	97.43	0.28	3.85	2.55	2.36	2.42	2.27	65.29	1.90	56.30	2	2051	92.22	63.82	6.39	56.36	1954	8.42	0.49	26300	37000	52400	26100	186	253	325	139	338	26.3	15.1	12.2	21	0	0.87	73.70	54.85	85.55	91.51	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	39.2	1515.3	0.70	?	?	?	?	0.00	?	8	13.13	34	55.79	98	160.8	128	210.02	608	997.6	2250	3691.79	125	205.1	9	14.77	439.73	4909.26
8	Fargocity	ND	17	25700	1	74111	2.46	0.35	97.11	1.25	0.73	16.64	35.16	20.33	8.58	74115	100.0	25326	83.69	2.93	47.11	19.30	4.21	10.31	34269	13554	13727	8852	5344	8011	5332	5174	9603	13.68	5.52	11.27	30.24	4.18	68.51	6.89	31.55	11.37	29.43	7.29	40.87	9.94	8.64	3.00	79.35	79.70	86.60	80.70	74.32	78.51	751	1.64	1474	23.68	33.58	46.68	53.93	0.47	0.67	0.93	1.07	95.21	0.43	2.59	1.54	2.32	2.77	1.91	57.42	1.67	59.32	2	1562	95.07	48.10	0.45	25.61	1971	2.66	0.19	54500	70300	93700	39200	241	321	387	146	355	25.2	20.7	12.8	125	15	1.99	58.82	40.72	67.97	81.39	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	?	30.9	2399.3	1.41	?	?	?	?	0.00	?	0	0.00	35	43.87	16	20.05	41	51.39	425	532.66	3149	3946.71	206	258.18	8	10.03	115.31	4747.58
9	Wacocity	TX	?	?	1	103590	2.62	23.14	67.60	0.92	16.35	19.88	34.55	21.62	13.12	103590	100.0	17852	74.20	0.86	30.98	29.09	9.06	13.99	24058	10195	12126	5715	11313	5770	7320	6984	27767	28.68	13.01	31.62	17.02	8.39	51.37	15.73	29.06	16.43	24.30	11.07	38.49	14.66	12.97	3.11	61.65	54.56	68.85	61.69	60.80	69.23	3537	4.71	4793	15.54	23.08	35.32	49.82	0.72	1.07	1.63	2.31	85.72	2.51	6.70	4.10	2.45	2.47	2.44	46.82	6.14	59.96	2	5606	87.57	46.51	5.64	37.57	1960	11.74	0.33	28600	43100	67400	38800	192	281	369	177	353	29.6	19.4	13.0	43	4	4.63	75.59	42.33	74.05	92.12	198	183.53	187	173.33	73432	68065.1	370.9	183.5	89.32	78.28	11.11	10.61	0	21.72	13	12	60.2	78.5	1319.3	0.76	100	9315474	94.44	10	6.57	86346.3	29	26.88	141	130.69	453	419.89	1043	966.77	2397	2221.81	6121	5673.63	1070	991.8	18	16.68	1544.24	8903.93

	communityname	state	countyCode	communityCode	fold	population	householdsize	racepctblack	racePctWhite	racePctAsian	racePctHisp	agePct12t21	agePct12t29	agePct16t24	agePct65up	numbUrban	pctUrban	medIncome	pctWWage	pctWFarmSelf	pctWInvInc	pctWSocSec	pctWPubAsst	pctWRetire	medFamInc	perCapInc	whitePerCap	blackPerCap	indianPerCap	AsianPerCap	OtherPerCap	HispPerCap	NumUnderPov	PctPopUnderPov	PctLess9thGrade	PctNotHSGrad	PctBSorMore	PctUnemployed	PctEmploy	PctEmplManu	PctEmplProfServ	PctOccupManu	PctOccupMgmtProf	MalePctDivorce	MalePctNevMarr	FemalePctDiv	TotalPctDiv	PersPerFam	PctFam2Par	PctKids2Par	PctYoungKids2Par	PctTeen2Par	PctWorkMomYoungKids	PctWorkMom	NumKidsBornNeverMar	PctKidsBornNeverMar	NumImmig	PctImmigRecent	PctImmigRec5	PctImmigRec8	PctImmigRec10	PctRecentImmig	PctRecImmig5	PctRecImmig8	PctRecImmig10	PctSpeakEnglOnly	PctNotSpeakEnglWell	PctLargHouseFam	PctLargHouseOccup	PersPerOccupHous	PersPerOwnOccHous	PersPerRentOccHous	PctPersOwnOccup	PctPersDenseHous	PctHousLess3BR	MedNumBR	HousVacant	PctHousOccup	PctHousOwnOcc	PctVacantBoarded	PctVacMore6Mos	MedYrHousBuilt	PctHousNoPhone	PctWOFullPlumb	OwnOccLowQuart	OwnOccMedVal	OwnOccHiQuart	OwnOccQrange	RentLowQ	RentMedian	RentHighQ	RentQrange	MedRent	MedRentPctHousInc	MedOwnCostPctInc	MedOwnCostPctIncNoMtg	NumInShelters	NumStreet	PctForeignBorn	PctBornSameState	PctSameHouse85	PctSameCity85	PctSameState85	LemasSwornFT	LemasSwFTPerPop	LemasSwFTFieldOps	LemasSwFTFieldPerPop	LemasTotalReq	LemasTotReqPerPop	PolicReqPerOffic	PolicPerPop	RacialMatchCommPol	PctPolicWhite	PctPolicBlack	PctPolicHisp	PctPolicAsian	PctPolicMinor	OfficAssgnDrugUnits	NumKindsDrugsSeiz	PolicAveOTWorked	LandArea	PopDens	PctUsePubTrans	PolicCars	PolicOperBudg	LemasPctPolicOnPatr	LemasGangUnitDeploy	LemasPctOfficDrugUn	PolicBudgPerPop	murders	murdPerPop	rapes	rapesPerPop	robberies	robbbPerPop	assaults	assaultPerPop	burglaries	burglPerPop	larcenies	larcPerPop	autoTheft	autoTheftPerPop	arsons	arsonsPerPop	ViolentCrimesPerPop	nonViolPerPop
0	BerkeleyHeightstownship	NJ	39.0	5320.0	1	11980	3.10	1.37	91.78	6.50	1.88	12.47	21.44	10.93	11.33	11980	100.0	75122	89.24	1.55	70.20	23.62	1.03	18.39	79584	29711	30233	13600	5725	27101	5115.0	22838	227	1.96	5.81	9.90	48.18	2.70	64.55	14.65	28.82	5.49	50.73	3.67	26.38	5.22	4.47	3.22	91.43	90.17	95.78	95.81	44.56	58.88	31	0.36	1277	8.69	13.00	20.99	30.93	0.93	1.39	2.24	3.30	85.68	1.37	4.81	4.17	2.99	3.00	2.84	91.46	0.39	11.06	3	64	98.37	91.01	3.12	37.50	1959	0.00	0.28	215900	262600	326900	111000	685	1001	1001	316	1001	23.8	21.1	14.0	11	0	10.66	53.72	65.29	78.09	89.14	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	6.5	1845.9	9.63	NaN	NaN	NaN	NaN	0.00	NaN	0	0.00	0.0	0.00	1.0	8.20	4.0	32.81	14.0	114.85	138.0	1132.08	16.0	131.26	2.0	16.41	41.02	1394.59
1	Marpletownship	PA	45.0	47616.0	1	23123	2.82	0.80	95.57	3.44	0.85	11.01	21.30	10.48	17.18	23123	100.0	47917	78.99	1.11	64.11	35.50	2.75	22.85	55323	20148	20191	18137	0	20074	5250.0	12222	885	3.98	5.61	13.72	29.89	2.43	61.96	12.26	29.28	6.39	37.64	4.23	27.99	6.45	5.42	3.11	86.91	85.33	96.82	86.46	51.14	62.43	43	0.24	1920	5.21	8.65	13.33	22.50	0.43	0.72	1.11	1.87	87.79	1.81	4.25	3.34	2.70	2.83	1.96	89.03	1.01	23.60	3	240	97.15	84.88	0.00	18.33	1958	0.31	0.14	136300	164200	199900	63600	467	560	672	205	627	27.6	20.7	12.5	0	0	8.30	77.17	71.27	90.22	96.12	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	10.6	2186.7	3.84	NaN	NaN	NaN	NaN	0.00	NaN	0	0.00	1.0	4.25	5.0	21.26	24.0	102.05	57.0	242.37	376.0	1598.78	26.0	110.55	1.0	4.25	127.56	1955.95
2	Tigardcity	OR	NaN	NaN	1	29344	2.43	0.74	94.33	3.43	2.35	11.36	25.88	11.01	10.28	29344	100.0	35669	82.00	1.15	55.73	22.25	2.94	14.56	42112	16946	17103	16644	21606	15528	5954.0	8405	1389	4.75	2.80	9.09	30.13	4.01	69.80	15.95	21.52	8.79	32.48	10.10	25.78	14.76	12.55	2.95	78.54	78.85	92.37	75.72	66.08	74.19	164	0.88	1468	16.42	23.98	32.08	35.63	0.82	1.20	1.61	1.78	93.11	1.14	2.97	2.05	2.42	2.69	2.06	64.18	2.03	47.46	3	544	95.68	57.79	0.92	7.54	1976	1.55	0.12	74700	90400	112000	37300	370	428	520	150	484	24.1	21.7	11.6	16	0	5.00	44.77	36.60	61.26	82.85	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	10.6	2780.9	4.37	NaN	NaN	NaN	NaN	0.00	NaN	3	8.30	6.0	16.60	56.0	154.95	14.0	38.74	274.0	758.14	1797.0	4972.19	136.0	376.30	22.0	60.87	218.59	6167.51
3	Gloversvillecity	NY	35.0	29443.0	1	16656	2.40	1.70	97.35	0.50	0.70	12.55	25.20	12.19	17.57	0	0.0	20580	68.15	0.24	38.95	39.48	11.71	18.33	26501	10810	10909	9984	4941	3541	2451.0	4391	2831	17.23	11.05	33.68	10.81	9.86	54.74	31.22	27.43	26.76	22.71	10.98	28.15	14.47	12.91	2.98	64.02	62.36	65.38	67.43	59.59	70.27	561	3.84	339	13.86	13.86	15.34	15.34	0.28	0.28	0.31	0.31	94.98	0.56	3.93	2.56	2.37	2.51	2.20	58.18	1.21	45.66	3	669	91.19	54.89	2.54	57.85	1939	7.00	0.87	36400	49600	66500	30100	195	250	309	114	333	28.7	20.6	14.5	0	0	2.04	88.71	56.70	90.17	96.24	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	5.2	3217.7	3.31	NaN	NaN	NaN	NaN	0.00	NaN	0	0.00	10.0	57.86	10.0	57.86	33.0	190.93	225.0	1301.78	716.0	4142.56	47.0	271.93	NaN	NaN	306.64	NaN
4	Bemidjicity	MN	7.0	5068.0	1	11245	2.76	0.53	89.16	1.17	0.52	24.46	40.53	28.69	12.65	0	0.0	17390	69.33	0.55	42.82	32.16	11.21	14.43	24018	8483	9009	887	4425	3352	3000.0	1328	2855	29.99	12.15	23.06	25.28	9.08	52.44	6.89	36.54	10.94	27.80	7.51	50.66	11.64	9.73	2.98	58.59	55.20	66.51	79.17	61.22	68.94	402	4.70	196	46.94	56.12	67.86	69.90	0.82	0.98	1.18	1.22	94.64	0.39	5.23	3.11	2.35	2.55	2.12	58.13	2.94	55.64	2	333	92.45	53.57	3.90	42.64	1958	7.45	0.82	30600	43200	59500	28900	202	283	362	160	332	32.2	23.2	12.9	2	0	1.74	73.75	42.22	60.34	89.02	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	11.5	974.2	0.38	NaN	NaN	NaN	NaN	0.00	NaN	0	0.00	NaN	NaN	4.0	32.04	14.0	112.14	91.0	728.93	1060.0	8490.87	91.0	728.93	5.0	40.05	NaN	9988.79
5	Springfieldcity	MO	NaN	NaN	1	140494	2.45	2.51	95.65	0.90	0.95	18.09	32.89	20.04	13.26	140494	100.0	21577	75.78	1.00	41.15	29.31	7.12	14.09	27705	11878	12029	7382	10264	10753	7192.0	8104	23223	17.78	8.76	23.03	20.66	5.72	59.02	14.31	26.83	14.72	23.42	11.40	33.32	14.46	13.04	2.89	71.94	69.79	79.76	75.33	62.96	70.52	1511	1.58	2091	21.33	30.56	38.02	45.48	0.32	0.45	0.57	0.68	96.87	0.60	3.08	1.92	2.28	2.37	2.16	57.81	2.11	53.19	2	5119	91.81	55.50	2.09	26.22	1966	6.13	0.31	37700	53900	73100	35400	215	280	349	134	340	26.4	17.3	11.7	327	4	1.49	64.35	42.29	70.61	85.66	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	70.4	1995.7	0.97	NaN	NaN	NaN	NaN	0.00	NaN	7	4.63	77.0	50.98	136.0	90.05	449.0	297.29	2094.0	1386.46	7690.0	5091.64	454.0	300.60	134.0	88.72	442.95	6867.42
6	Norwoodtown	MA	21.0	50250.0	1	28700	2.60	1.60	96.57	1.47	1.10	11.17	27.41	12.76	14.42	28700	100.0	42805	79.47	0.39	47.70	30.23	5.41	17.23	50394	18193	18276	17342	21482	12639	21852.0	22594	1126	4.01	4.49	13.89	27.01	4.85	65.42	14.02	27.17	8.50	32.78	5.97	36.05	9.06	7.64	3.14	79.53	79.76	92.05	77.12	65.16	72.81	263	1.18	2637	11.38	16.27	23.93	27.76	1.05	1.49	2.20	2.55	89.98	0.60	5.08	3.46	2.55	2.89	2.09	64.62	1.47	47.35	3	566	95.11	56.96	1.41	34.45	1956	0.69	0.28	155100	179000	215500	60400	463	669	824	361	736	24.4	20.8	12.5	0	0	9.19	77.30	63.45	82.23	93.53	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	10.9	2643.5	9.62	NaN	NaN	NaN	NaN	0.00	NaN	0	0.00	4.0	13.53	9.0	30.44	54.0	182.66	110.0	372.09	288.0	974.19	144.0	487.10	17.0	57.50	226.63	1890.88
7	Andersoncity	IN	NaN	NaN	1	59459	2.45	14.20	84.87	0.40	0.63	15.31	27.93	14.78	14.60	59449	100.0	23221	71.60	0.67	35.74	32.58	8.81	22.59	28901	12161	12599	9820	6634	8802	7428.0	6187	10320	17.98	10.09	28.67	12.00	8.19	56.59	27.00	21.54	21.92	18.02	13.28	28.34	16.33	14.94	2.95	62.56	58.70	69.89	62.76	63.08	72.44	2368	4.66	517	13.15	22.82	28.24	33.08	0.11	0.20	0.25	0.29	97.43	0.28	3.85	2.55	2.36	2.42	2.27	65.29	1.90	56.30	2	2051	92.22	63.82	6.39	56.36	1954	8.42	0.49	26300	37000	52400	26100	186	253	325	139	338	26.3	15.1	12.2	21	0	0.87	73.70	54.85	85.55	91.51	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	39.2	1515.3	0.70	NaN	NaN	NaN	NaN	0.00	NaN	8	13.13	34.0	55.79	98.0	160.80	128.0	210.02	608.0	997.60	2250.0	3691.79	125.0	205.10	9.0	14.77	439.73	4909.26
8	Fargocity	ND	17.0	25700.0	1	74111	2.46	0.35	97.11	1.25	0.73	16.64	35.16	20.33	8.58	74115	100.0	25326	83.69	2.93	47.11	19.30	4.21	10.31	34269	13554	13727	8852	5344	8011	5332.0	5174	9603	13.68	5.52	11.27	30.24	4.18	68.51	6.89	31.55	11.37	29.43	7.29	40.87	9.94	8.64	3.00	79.35	79.70	86.60	80.70	74.32	78.51	751	1.64	1474	23.68	33.58	46.68	53.93	0.47	0.67	0.93	1.07	95.21	0.43	2.59	1.54	2.32	2.77	1.91	57.42	1.67	59.32	2	1562	95.07	48.10	0.45	25.61	1971	2.66	0.19	54500	70300	93700	39200	241	321	387	146	355	25.2	20.7	12.8	125	15	1.99	58.82	40.72	67.97	81.39	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	30.9	2399.3	1.41	NaN	NaN	NaN	NaN	0.00	NaN	0	0.00	35.0	43.87	16.0	20.05	41.0	51.39	425.0	532.66	3149.0	3946.71	206.0	258.18	8.0	10.03	115.31	4747.58
9	Wacocity	TX	NaN	NaN	1	103590	2.62	23.14	67.60	0.92	16.35	19.88	34.55	21.62	13.12	103590	100.0	17852	74.20	0.86	30.98	29.09	9.06	13.99	24058	10195	12126	5715	11313	5770	7320.0	6984	27767	28.68	13.01	31.62	17.02	8.39	51.37	15.73	29.06	16.43	24.30	11.07	38.49	14.66	12.97	3.11	61.65	54.56	68.85	61.69	60.80	69.23	3537	4.71	4793	15.54	23.08	35.32	49.82	0.72	1.07	1.63	2.31	85.72	2.51	6.70	4.10	2.45	2.47	2.44	46.82	6.14	59.96	2	5606	87.57	46.51	5.64	37.57	1960	11.74	0.33	28600	43100	67400	38800	192	281	369	177	353	29.6	19.4	13.0	43	4	4.63	75.59	42.33	74.05	92.12	198.0	183.53	187.0	173.33	73432.0	68065.1	370.9	183.5	89.32	78.28	11.11	10.61	0.0	21.72	13.0	12.0	60.2	78.5	1319.3	0.76	100.0	9315474.0	94.44	10.0	6.57	86346.3	29	26.88	141.0	130.69	453.0	419.89	1043.0	966.77	2397.0	2221.81	6121.0	5673.63	1070.0	991.80	18.0	16.68	1544.24	8903.93

	countyCode	communityCode	fold	population	householdsize	racepctblack	racePctWhite	racePctAsian	racePctHisp	agePct12t21	agePct12t29	agePct16t24	agePct65up	numbUrban	pctUrban	medIncome	pctWWage	pctWFarmSelf	pctWInvInc	pctWSocSec	pctWPubAsst	pctWRetire	medFamInc	perCapInc	whitePerCap	blackPerCap	indianPerCap	AsianPerCap	OtherPerCap	HispPerCap	NumUnderPov	PctPopUnderPov	PctLess9thGrade	PctNotHSGrad	PctBSorMore	PctUnemployed	PctEmploy	PctEmplManu	PctEmplProfServ	PctOccupManu	PctOccupMgmtProf	MalePctDivorce	MalePctNevMarr	FemalePctDiv	TotalPctDiv	PersPerFam	PctFam2Par	PctKids2Par	PctYoungKids2Par	PctTeen2Par	PctWorkMomYoungKids	PctWorkMom	NumKidsBornNeverMar	PctKidsBornNeverMar	NumImmig	PctImmigRecent	PctImmigRec5	PctImmigRec8	PctImmigRec10	PctRecentImmig	PctRecImmig5	PctRecImmig8	PctRecImmig10	PctSpeakEnglOnly	PctNotSpeakEnglWell	PctLargHouseFam	PctLargHouseOccup	PersPerOccupHous	PersPerOwnOccHous	PersPerRentOccHous	PctPersOwnOccup	PctPersDenseHous	PctHousLess3BR	MedNumBR	HousVacant	PctHousOccup	PctHousOwnOcc	PctVacantBoarded	PctVacMore6Mos	MedYrHousBuilt	PctHousNoPhone	PctWOFullPlumb	OwnOccLowQuart	OwnOccMedVal	OwnOccHiQuart	OwnOccQrange	RentLowQ	RentMedian	RentHighQ	RentQrange	MedRent	MedRentPctHousInc	MedOwnCostPctInc	MedOwnCostPctIncNoMtg	NumInShelters	NumStreet	PctForeignBorn	PctBornSameState	PctSameHouse85	PctSameCity85	PctSameState85	LemasSwornFT	LemasSwFTPerPop	LemasSwFTFieldOps	LemasSwFTFieldPerPop	LemasTotalReq	LemasTotReqPerPop	PolicReqPerOffic	PolicPerPop	RacialMatchCommPol	PctPolicWhite	PctPolicBlack	PctPolicHisp	PctPolicAsian	PctPolicMinor	OfficAssgnDrugUnits	NumKindsDrugsSeiz	PolicAveOTWorked	LandArea	PopDens	PctUsePubTrans	PolicCars	PolicOperBudg	LemasPctPolicOnPatr	LemasGangUnitDeploy	LemasPctOfficDrugUn	PolicBudgPerPop	murders	murdPerPop	rapes	rapesPerPop	robberies	robbbPerPop	assaults	assaultPerPop	burglaries	burglPerPop	larcenies	larcPerPop	autoTheft	autoTheftPerPop	arsons	arsonsPerPop	ViolentCrimesPerPop	nonViolPerPop
count	994.000000	991.000000	2215.000000	2.215000e+03	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2.215000e+03	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2214.000000	2215.000000	2.215000e+03	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2.215000e+03	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	2215.000000	343.000000	343.000000	343.000000	343.000000	3.430000e+02	3.430000e+02	343.000000	343.000000	343.000000	343.000000	343.000000	343.000000	343.000000	343.000000	343.000000	343.000000	343.000000	2215.000000	2215.000000	2215.000000	343.000000	3.430000e+02	343.000000	343.000000	2215.000000	3.430000e+02	2215.000000	2215.000000	2007.000000	2007.00000	2214.000000	2214.000000	2202.000000	2202.000000	2212.000000	2212.000000	2212.000000	2212.000000	2212.000000	2212.000000	2124.000000	2124.000000	1994.000000	2118.000000
mean	65.587525	45209.251261	5.494357	5.311798e+04	2.707327	9.335102	83.979819	2.670203	7.950176	14.445837	27.644840	13.975142	11.836393	4.773472e+04	70.465309	33984.696163	78.312758	0.881842	43.750935	26.409418	6.801445	15.969002	39857.055079	15603.524605	16567.698420	11541.749436	12229.191422	14227.989616	9442.765131	11018.998194	7.590853e+03	11.620537	9.186646	22.305120	23.056876	6.045242	62.021612	18.228907	24.532298	13.819165	28.209201	9.127585	30.683517	12.325300	10.812515	3.129698	74.059129	71.227255	81.865422	75.521788	60.542641	68.854795	2141.418962	3.115499	6.277274e+03	13.525693	20.421287	27.544181	34.733928	1.099124	1.697463	2.307503	2.943761	87.074993	2.405792	5.386619	3.915788	2.615842	2.740483	2.367138	66.369454	4.132438	45.405341	2.640632	1748.368849	92.933973	63.368298	2.778524	34.773887	1962.623476	4.289824	0.425273	88695.802257	113097.523251	145318.257788	56622.455530	329.966591	428.537246	527.252822	197.286230	501.466366	26.298104	20.990158	13.010203	66.953499	17.823476	7.340302	61.539630	51.538596	77.411079	88.111865	499.198251	246.490962	432.559767	210.844781	2.524050e+05	1.206517e+05	523.658309	246.493586	85.499679	82.515831	9.263294	5.459767	0.681283	15.242245	26.288630	8.816327	119.114286	27.419955	2783.835034	3.041124	185.478134	3.217602e+07	87.130933	4.285714	0.980163	1.535779e+05	7.764786	5.859296	28.046338	36.25848	237.952123	162.612597	326.528156	378.004605	761.236890	1033.430203	2137.629295	3372.979150	516.692586	473.965628	30.907721	32.153682	589.078922	4908.241804
std	117.831399	25425.861573	2.872924	2.046203e+05	0.334120	14.247156	16.419080	4.473843	14.589832	4.518623	6.181517	5.970747	4.777565	2.056067e+05	44.080275	13424.680011	7.950672	0.689006	12.787925	8.295604	4.700335	4.622553	14251.206032	6281.558523	6346.840251	9232.102062	14853.836177	9881.266395	7926.466713	5884.063446	3.936146e+04	8.600352	6.666703	10.989517	12.687213	2.895618	8.312045	8.099281	6.659470	6.430264	9.326123	2.802747	8.127991	3.262613	3.000883	0.240743	10.525952	12.045048	12.263736	10.365262	8.008937	6.679960	14692.582838	3.127681	5.541965e+04	9.780098	12.410355	14.368813	16.327322	1.595766	2.461060	3.286648	4.246468	14.076087	4.210368	3.794309	3.175770	0.315646	0.297421	0.391806	14.182588	5.599131	13.778347	0.512686	6503.866478	5.040736	13.970057	3.592396	13.911468	11.166555	4.088175	0.426188	66670.781534	81906.362277	99030.913816	39106.498041	144.138461	170.706644	199.290780	85.205688	169.271735	2.979297	2.987622	1.419679	564.253149	245.452553	8.418476	16.750061	10.517926	10.878186	7.287836	1681.472251	273.799162	1493.708385	235.478815	6.894498e+05	1.482113e+05	307.839007	273.798409	10.941312	15.332612	11.021424	10.604533	1.706344	14.826756	100.821921	2.836391	92.495186	109.822600	2828.993341	4.912917	318.542834	1.104566e+08	10.349612	4.064538	2.877128	2.030409e+05	58.166468	9.156829	105.616135	34.23975	2250.720788	234.486624	1987.947941	438.238599	3111.702756	763.354442	7600.573464	1901.316145	3258.164244	504.666026	180.125248	39.240900	614.784518	2739.708901
min	1.000000	70.000000	1.000000	1.000500e+04	1.600000	0.000000	2.680000	0.030000	0.120000	4.580000	9.380000	4.640000	1.660000	0.000000e+00	0.000000	8866.000000	31.680000	0.000000	5.810000	4.810000	0.180000	3.460000	10447.000000	5237.000000	5472.000000	0.000000	0.000000	0.000000	0.000000	0.000000	7.800000e+01	0.640000	0.200000	1.460000	1.630000	1.320000	24.820000	2.050000	8.690000	1.370000	6.480000	2.130000	12.060000	3.350000	2.830000	2.290000	22.970000	18.300000	8.700000	20.200000	24.420000	41.950000	0.000000	0.000000	2.000000e+01	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	6.150000	0.000000	0.960000	0.440000	1.580000	1.610000	1.550000	13.930000	0.050000	3.060000	1.000000	36.000000	37.470000	16.860000	0.000000	3.120000	1939.000000	0.000000	0.000000	14999.000000	19500.000000	28200.000000	0.000000	99.000000	120.000000	182.000000	0.000000	192.000000	14.900000	14.000000	10.100000	0.000000	0.000000	0.180000	6.750000	11.830000	27.950000	32.830000	65.000000	29.400000	14.000000	19.210000	2.100000e+03	2.704800e+03	20.800000	29.400000	42.150000	1.600000	0.000000	0.000000	0.000000	0.000000	0.000000	1.000000	0.000000	0.900000	10.000000	0.000000	20.000000	2.380215e+06	10.850000	0.000000	0.000000	1.526040e+04	0.000000	0.000000	0.000000	0.00000	0.000000	0.000000	0.000000	0.000000	2.000000	16.920000	10.000000	77.860000	1.000000	6.550000	0.000000	0.000000	0.000000	116.790000
25%	11.000000	22887.000000	3.000000	1.436600e+04	2.500000	0.860000	76.320000	0.620000	0.930000	12.250000	24.415000	11.320000	8.750000	0.000000e+00	0.000000	23817.000000	73.400000	0.460000	34.680000	20.770000	3.270000	12.875000	29538.000000	11602.500000	12610.500000	6742.500000	6345.000000	8285.500000	5528.250000	7274.000000	9.125000e+02	4.510000	4.640000	13.920000	14.095000	4.045000	56.490000	12.215000	20.075000	9.130000	21.910000	7.110000	25.450000	9.860000	8.575000	2.990000	67.900000	63.990000	74.780000	70.170000	55.430000	64.900000	147.000000	1.070000	4.000000e+02	6.695000	11.255000	17.205000	22.725000	0.170000	0.280000	0.390000	0.520000	84.380000	0.510000	3.390000	2.370000	2.410000	2.550000	2.110000	57.285000	1.290000	37.505000	2.000000	304.500000	91.290000	54.820000	0.720000	24.480000	1956.000000	0.905000	0.160000	41500.000000	56200.000000	74300.000000	32200.000000	213.500000	289.500000	366.000000	139.000000	364.000000	24.300000	18.700000	12.000000	0.000000	0.000000	2.060000	50.110000	44.995000	72.060000	85.200000	131.000000	149.115000	114.000000	132.245000	4.986450e+04	6.484505e+04	343.350000	149.150000	79.435000	76.230000	2.020000	0.415000	0.000000	4.950000	6.000000	7.000000	55.100000	7.300000	1181.900000	0.360000	54.000000	7.275060e+06	84.295000	0.000000	0.000000	8.809435e+04	0.000000	0.000000	2.000000	11.53500	5.000000	27.647500	18.000000	94.187500	95.000000	511.690000	392.000000	2040.080000	30.000000	156.952500	1.000000	7.670000	161.700000	2918.070000
50%	27.000000	46925.000000	5.000000	2.279200e+04	2.660000	2.870000	90.350000	1.230000	2.180000	13.620000	26.780000	12.540000	11.730000	1.804100e+04	100.000000	31441.000000	78.610000	0.690000	42.880000	26.590000	5.610000	15.650000	36678.000000	14101.000000	15073.000000	9777.000000	9895.000000	12250.000000	8186.000000	9721.000000	2.142000e+03	9.330000	7.740000	21.380000	19.650000	5.450000	62.440000	17.300000	23.390000	13.150000	26.240000	9.150000	29.000000	12.520000	10.900000	3.100000	75.030000	72.530000	83.990000	76.920000	60.710000	69.230000	352.000000	2.040000	1.024000e+03	12.260000	19.080000	26.720000	34.790000	0.500000	0.750000	1.040000	1.310000	92.180000	0.920000	4.280000	3.050000	2.570000	2.710000	2.290000	65.910000	2.340000	46.390000	3.000000	558.000000	94.210000	62.830000	1.660000	34.100000	1964.000000	2.850000	0.320000	65500.000000	82800.000000	106700.000000	43400.000000	307.000000	397.000000	486.000000	171.000000	467.000000	26.100000	21.000000	12.800000	0.000000	0.000000	4.310000	64.490000	52.170000	79.490000	90.030000	173.000000	196.010000	152.000000	170.270000	9.000000e+04	9.103460e+04	443.200000	196.000000	87.930000	86.180000	5.000000	2.040000	0.000000	11.370000	12.000000	9.000000	98.700000	13.700000	2027.300000	1.220000	86.000000	1.116411e+07	89.580000	5.000000	0.000000	1.145820e+05	1.000000	2.170000	7.000000	26.92000	19.000000	74.800000	56.000000	226.525000	205.000000	822.715000	747.000000	3079.510000	75.000000	302.355000	5.000000	21.080000	374.060000	4425.450000
75%	80.500000	65805.000000	8.000000	4.302400e+04	2.850000	11.145000	96.225000	2.670000	7.810000	15.360000	29.205000	14.345000	14.415000	4.191800e+04	100.000000	41480.500000	84.030000	1.100000	52.740000	31.715000	9.105000	18.755000	46999.000000	17795.000000	18609.500000	14526.000000	14757.500000	17327.500000	11525.500000	13418.000000	4.988000e+03	16.905000	11.835000	29.195000	29.055000	7.440000	67.825000	23.400000	27.590000	17.665000	32.815000	11.050000	33.410000	14.745000	12.985000	3.220000	81.900000	80.395000	91.675000	82.765000	65.985000	73.495000	1031.500000	3.910000	3.302000e+03	17.950000	27.445000	36.495000	46.185000	1.310000	2.015000	2.700000	3.455000	95.455000	2.270000	5.870000	4.210000	2.770000	2.900000	2.530000	76.580000	4.730000	53.515000	3.000000	1228.000000	96.020000	72.645000	3.430000	43.970000	1971.000000	6.805000	0.555000	121500.000000	150600.000000	188000.000000	65450.000000	421.000000	544.000000	659.500000	232.500000	615.000000	28.000000	23.100000	13.700000	22.000000	1.000000	9.250000	74.855000	58.740000	85.135000	93.010000	314.000000	260.650000	285.500000	226.815000	1.719235e+05	1.303246e+05	637.250000	260.650000	93.645000	93.340000	14.065000	6.215000	0.650000	19.740000	23.000000	10.500000	153.550000	26.100000	3321.700000	3.365000	189.500000	2.014754e+07	93.200000	10.000000	0.000000	1.556557e+05	3.000000	8.365000	19.000000	51.47000	70.000000	187.155000	180.000000	504.387500	508.000000	1350.232500	1675.000000	4335.410000	232.500000	589.775000	16.000000	42.852500	794.400000	6229.280000
max	840.000000	94597.000000	10.000000	7.322564e+06	5.280000	96.670000	99.630000	57.460000	95.290000	54.400000	70.510000	63.620000	52.770000	7.322564e+06	100.000000	123625.000000	96.760000	6.530000	89.040000	76.390000	44.820000	45.510000	139008.000000	63302.000000	68850.000000	212120.000000	480000.000000	106165.000000	137000.000000	54648.000000	1.384994e+06	58.000000	49.890000	73.660000	79.180000	31.230000	84.670000	50.030000	62.670000	44.270000	64.970000	20.080000	76.600000	23.920000	22.230000	4.640000	93.600000	92.580000	100.000000	97.340000	87.970000	89.370000	527557.000000	27.350000	2.082931e+06	64.290000	76.160000	80.810000	88.000000	13.710000	19.930000	25.340000	32.630000	98.980000	38.330000	34.870000	30.870000	4.520000	4.480000	4.730000	97.240000	59.490000	95.340000	4.000000	172768.000000	99.000000	96.490000	39.890000	82.130000	1987.000000	23.880000	5.330000	500001.000000	500001.000000	500001.000000	331000.000000	1001.000000	1001.000000	1001.000000	803.000000	1001.000000	35.100000	32.700000	23.400000	23383.000000	10447.000000	60.400000	93.140000	78.560000	96.590000	99.900000	25655.000000	3437.230000	22496.000000	3290.620000	8.328470e+06	1.926282e+06	2162.500000	3437.200000	100.000000	100.000000	67.310000	98.400000	18.570000	98.400000	1773.000000	15.000000	634.700000	3569.800000	44229.900000	54.330000	3187.000000	1.617293e+09	99.940000	10.000000	48.440000	2.422367e+06	1946.000000	91.090000	2818.000000	401.35000	86001.000000	2264.130000	62778.000000	4932.500000	99207.000000	11881.020000	235132.000000	25910.550000	112464.000000	4968.590000	5119.000000	436.370000	4877.060000	27119.760000

	countyCode	communityCode	fold	population	householdsize	racepctblack	racePctWhite	racePctAsian	racePctHisp	agePct12t21	agePct12t29	agePct16t24	agePct65up	numbUrban	pctUrban	medIncome	pctWWage	pctWFarmSelf	pctWInvInc	pctWSocSec	pctWPubAsst	pctWRetire	medFamInc	perCapInc	whitePerCap	blackPerCap	indianPerCap	AsianPerCap	OtherPerCap	HispPerCap	NumUnderPov	PctPopUnderPov	PctLess9thGrade	PctNotHSGrad	PctBSorMore	PctUnemployed	PctEmploy	PctEmplManu	PctEmplProfServ	PctOccupManu	PctOccupMgmtProf	MalePctDivorce	MalePctNevMarr	FemalePctDiv	TotalPctDiv	PersPerFam	PctFam2Par	PctKids2Par	PctYoungKids2Par	PctTeen2Par	PctWorkMomYoungKids	PctWorkMom	NumKidsBornNeverMar	PctKidsBornNeverMar	NumImmig	PctImmigRecent	PctImmigRec5	PctImmigRec8	PctImmigRec10	PctRecentImmig	PctRecImmig5	PctRecImmig8	PctRecImmig10	PctSpeakEnglOnly	PctNotSpeakEnglWell	PctLargHouseFam	PctLargHouseOccup	PersPerOccupHous	PersPerOwnOccHous	PersPerRentOccHous	PctPersOwnOccup	PctPersDenseHous	PctHousLess3BR	MedNumBR	HousVacant	PctHousOccup	PctHousOwnOcc	PctVacantBoarded	PctVacMore6Mos	MedYrHousBuilt	PctHousNoPhone	PctWOFullPlumb	OwnOccLowQuart	OwnOccMedVal	OwnOccHiQuart	OwnOccQrange	RentLowQ	RentMedian	RentHighQ	RentQrange	MedRent	MedRentPctHousInc	MedOwnCostPctInc	MedOwnCostPctIncNoMtg	NumInShelters	NumStreet	PctForeignBorn	PctBornSameState	PctSameHouse85	PctSameCity85	PctSameState85	LemasSwornFT	LemasSwFTPerPop	LemasSwFTFieldOps	LemasSwFTFieldPerPop	LemasTotalReq	LemasTotReqPerPop	PolicReqPerOffic	PolicPerPop	RacialMatchCommPol	PctPolicWhite	PctPolicBlack	PctPolicHisp	PctPolicAsian	PctPolicMinor	OfficAssgnDrugUnits	NumKindsDrugsSeiz	PolicAveOTWorked	LandArea	PopDens	PctUsePubTrans	PolicCars	PolicOperBudg	LemasPctPolicOnPatr	LemasGangUnitDeploy	LemasPctOfficDrugUn	PolicBudgPerPop	murders	murdPerPop	rapes	rapesPerPop	robberies	robbbPerPop	assaults	assaultPerPop	burglaries	burglPerPop	larcenies	larcPerPop	autoTheft	autoTheftPerPop	arsons	arsonsPerPop	ViolentCrimesPerPop	nonViolPerPop
state
AK	NaN	NaN	7.333333	94644.000000	2.756667	6.826667	77.906667	4.136667	4.086667	13.986667	29.586667	13.966667	4.303333	73915.000000	32.656667	41301.000000	89.586667	1.083333	74.923333	10.960000	6.843333	13.766667	46051.333333	18068.333333	19928.333333	12596.666667	10115.333333	12005.333333	12153.000000	11534.666667	6681.666667	7.683333	3.480000	11.176667	25.300000	6.610000	72.913333	3.343333	24.726667	8.743333	31.840000	12.896667	31.660000	16.116667	14.440000	3.196667	74.700000	73.003333	81.053333	78.000000	63.173333	72.633333	1865.333333	3.133333	5397.333333	12.216667	20.800000	32.660000	40.870000	0.653333	1.106667	1.730000	2.153333	90.686667	1.236667	5.390000	3.676667	2.653333	2.783333	2.503333	49.940000	5.586667	53.32000	2.333333	4613.000000	89.246667	47.370000	5.843333	39.796667	1973.666667	5.483333	1.216667	78433.333333	102866.666667	132533.333333	54100.000000	407.000000	527.333333	673.666667	266.666667	580.000000	24.900000	21.500000	11.300000	130.000000	25.000000	5.243333	28.786667	35.826667	64.576667	72.073333	266.000000	104.930000	252.000000	99.410000	107811.000000	42529.000000	405.300000	104.900000	89.390000	89.470000	4.140000	1.880000	2.630000	8.650000	16.000000	11.000000	0.000000	1492.733333	363.033333	2.916667	301.000000	2.941312e+07	94.740000	10.000000	2.006667	116028.100000	9.666667	8.870000	83.000000	66.080000	217.000000	156.103333	523.666667	345.516667	753.000000	639.463333	4325.666667	3813.090000	562.333333	485.286667	38.000000	23.833333	576.576667	4961.673333
AL	NaN	NaN	6.000000	39231.186047	2.611860	27.044651	71.799535	0.750000	0.665116	16.117209	28.540233	15.227209	12.415581	34182.069767	64.992558	26034.860465	75.144419	0.855814	33.825349	28.445814	8.100930	15.898837	33033.232558	13065.651163	14933.186047	7357.930233	12009.325581	12114.069767	6510.232558	10418.418605	7405.232558	17.863256	11.406977	27.426279	23.013023	6.635581	57.156047	19.573953	26.390698	16.170233	28.505814	9.366047	29.517907	13.030698	11.367674	3.075116	69.230698	64.306744	76.904186	70.583023	63.534884	69.728837	1965.325581	4.789070	687.255814	18.807209	28.404186	33.491860	42.968140	0.294884	0.434419	0.531163	0.648837	96.534651	0.424186	4.433023	3.093023	2.520000	2.629767	2.335349	65.245581	2.924186	41.71000	2.860465	1366.395349	92.252093	62.581628	2.883953	37.815349	1966.976744	6.644186	0.640930	46648.837209	63955.813953	89079.069767	42430.232558	170.465116	246.697674	325.372093	154.906977	336.627907	25.218605	18.051163	12.688372	32.093023	7.883721	1.483488	71.264186	51.849767	78.885349	87.704419	293.833333	184.121667	252.500000	155.971667	141162.166667	87517.881667	431.033333	184.150000	81.233333	75.255000	23.325000	0.425000	0.720000	24.471667	14.333333	8.500000	164.500000	37.248837	1143.448837	0.523023	167.166667	1.356148e+07	81.938333	5.833333	0.753953	82293.251667	7.581395	11.342093	24.325581	42.825349	135.720930	199.333721	374.093023	777.197674	708.418605	1273.725814	1869.255814	3730.038605	260.720930	399.103953	30.812500	35.178750	1030.699070	6025.023750
AR	NaN	NaN	5.440000	32674.520000	2.652800	19.470000	78.883600	0.835600	0.979200	16.207600	29.028800	15.354400	12.666400	20450.480000	40.000000	22025.560000	73.618400	1.258000	32.592800	29.241200	8.465200	14.075200	27477.320000	11245.760000	12798.640000	7215.760000	8606.000000	10218.360000	9461.120000	7651.240000	5535.720000	18.780800	12.641600	29.064400	16.950800	6.596000	58.104000	19.264000	24.798400	17.750800	23.689200	10.165600	27.406400	13.674000	12.065200	3.058000	69.728400	65.208800	76.107600	71.822800	64.511200	71.568800	1191.000000	3.995200	547.760000	19.377200	25.513200	37.754800	43.952000	0.251600	0.360400	0.540400	0.656000	96.800800	0.546000	4.402000	3.130800	2.522800	2.589200	2.421600	62.018800	3.427600	45.65840	2.880000	1280.440000	91.835600	60.400000	3.585200	37.975200	1968.120000	9.751200	0.581600	37220.000000	51488.000000	71760.000000	34540.000000	176.960000	245.360000	313.600000	136.640000	339.800000	26.880000	19.428000	13.452000	15.200000	1.440000	1.369200	63.527600	48.319200	75.919200	85.816000	111.666667	147.090000	88.000000	117.630000	51710.000000	73882.933333	447.833333	147.100000	76.176667	85.573333	14.156667	0.000000	0.270000	14.426667	9.333333	7.333333	42.933333	26.832000	1241.868000	0.415200	70.666667	5.969266e+06	78.543333	3.333333	0.979600	67721.166667	5.680000	10.735600	25.440000	52.083600	102.600000	195.645600	290.560000	460.085200	652.680000	1450.826400	1856.600000	4575.336800	222.760000	450.897200	15.760000	32.514800	718.550400	6509.575600
AZ	NaN	NaN	5.700000	125811.650000	2.778500	2.610500	84.655500	1.574500	22.434500	14.850000	27.722500	13.808500	11.690500	114430.000000	54.660000	32264.500000	77.323000	0.952000	38.545500	25.294000	6.444000	16.827500	37024.700000	15380.050000	16208.950000	14505.700000	10459.250000	12970.100000	7450.900000	9127.850000	17101.050000	15.036500	9.917500	21.542500	21.650500	7.012000	59.707500	12.751500	22.172500	11.422000	27.247000	9.869000	28.504500	13.229000	11.610000	3.175000	74.329500	70.758500	82.037000	76.480000	58.645500	66.129000	3050.750000	2.618000	10154.800000	14.418000	23.323000	30.726000	37.103500	1.459000	2.286000	2.925500	3.545000	78.144000	4.111000	7.035500	5.244500	2.706500	2.793000	2.571500	65.994500	6.886500	49.96900	2.550000	7948.600000	84.915000	64.188000	1.902000	27.634500	1975.900000	6.852500	0.329000	72980.000000	95985.000000	128820.050000	55840.050000	311.200000	405.650000	499.500000	188.300000	476.700000	28.175000	22.770000	12.635000	125.350000	30.350000	9.245500	29.936000	39.551000	68.547000	74.233000	611.833333	139.425000	575.000000	130.758333	512103.833333	116322.850000	849.000000	139.416667	96.275000	89.226667	1.680000	8.370000	0.415000	10.463333	21.500000	11.000000	161.200000	78.850000	1375.160000	1.103000	366.833333	4.265164e+07	93.966667	6.666667	1.469500	98273.283333	12.400000	4.613500	58.600000	30.195000	292.500000	119.256000	810.000000	397.030000	2281.450000	1510.476500	6869.450000	4325.365000	1501.850000	661.164500	45.100000	35.179000	551.094500	6532.186000
CA	76.0	93325.0	5.591398	79654.179211	2.926129	5.312222	71.973799	9.480896	24.799427	13.974158	28.252581	13.678136	9.780287	76204.000000	85.266989	39655.982079	80.120394	0.827849	40.754624	21.825520	8.877240	14.881900	44720.125448	17465.885305	18957.817204	13960.465950	14410.684588	15125.035842	10407.967742	11528.028674	9958.157706	10.789140	10.443297	22.795986	23.964158	6.350860	63.222581	16.795376	22.322186	12.847097	28.926344	9.677957	32.928100	14.002688	11.870323	3.304301	74.187312	70.442652	83.169928	75.711541	56.891039	64.844875	2630.627240	3.391505	19501.440860	15.708638	24.847025	34.214588	43.798459	3.295878	5.196667	7.149247	9.209498	70.336953	7.405412	9.233799	7.007849	2.851111	2.885735	2.788244	59.075663	11.628315	51.37086	2.448029	1725.663082	94.359534	58.164552	1.918746	20.730000	1967.225806	2.712939	0.429749	175336.935484	219367.068100	269462.820789	94125.885305	490.584229	607.885305	732.716846	242.132616	665.078853	28.691756	24.844086	11.708602	100.139785	49.885305	19.687204	48.018280	44.247742	74.198208	87.774265	458.061224	157.247959	386.244898	134.820204	311710.979592	103479.571020	694.083673	157.248980	82.908571	74.932041	7.714694	10.421837	3.077551	20.878571	24.877551	9.591837	181.189796	33.169534	4693.495699	3.265878	173.734694	3.961899e+07	87.499388	6.020408	1.124695	154858.814490	11.727599	8.134588	32.491039	32.646882	406.215054	273.137276	535.151079	496.704964	1098.870968	1248.996595	2694.913978	3022.680896	965.017921	819.774265	55.698925	47.988530	810.469388	5139.440251

	murdPerPop	rapesPerPop	robbbPerPop	assaultPerPop	burglPerPop	larcPerPop	autoTheftPerPop	arsonsPerPop
state
AK	8.870000	66.080000	156.103333	345.516667	639.463333	3813.090000	485.286667	23.833333
AL	11.342093	42.825349	199.333721	777.197674	1273.725814	3730.038605	399.103953	35.178750
AR	10.735600	52.083600	195.645600	460.085200	1450.826400	4575.336800	450.897200	32.514800
AZ	4.613500	30.195000	119.256000	397.030000	1510.476500	4325.365000	661.164500	35.179000
CA	8.134588	32.646882	273.137276	496.704964	1248.996595	3022.680896	819.774265	47.988530
CO	3.822800	41.320400	84.554000	397.163600	965.632800	4010.375600	350.701200	42.820400
CT	3.841972	16.033239	111.564366	127.755217	740.837746	2372.257465	425.045070	19.466338
DC	81.950000	58.480000	1282.850000	1625.090000	2081.590000	5679.780000	1454.870000	36.100000
DE	0.000000	123.330000	267.210000	496.750000	859.880000	6118.530000	260.360000	37.680000
FL	7.305556	49.775889	359.934778	742.029556	1932.676667	5190.722333	866.247889	21.462111

	countyCode	communityCode	fold	population	householdsize	racepctblack	racePctWhite	racePctAsian	racePctHisp	agePct12t21	agePct12t29	agePct16t24	agePct65up	numbUrban	pctUrban	medIncome	pctWWage	pctWFarmSelf	pctWInvInc	pctWSocSec	pctWPubAsst	pctWRetire	medFamInc	perCapInc	whitePerCap	blackPerCap	indianPerCap	AsianPerCap	OtherPerCap	HispPerCap	NumUnderPov	PctPopUnderPov	PctLess9thGrade	PctNotHSGrad	PctBSorMore	PctUnemployed	PctEmploy	PctEmplManu	PctEmplProfServ	PctOccupManu	PctOccupMgmtProf	MalePctDivorce	MalePctNevMarr	FemalePctDiv	TotalPctDiv	PersPerFam	PctFam2Par	PctKids2Par	PctYoungKids2Par	PctTeen2Par	PctWorkMomYoungKids	PctWorkMom	NumKidsBornNeverMar	PctKidsBornNeverMar	NumImmig	PctImmigRecent	PctImmigRec5	PctImmigRec8	PctImmigRec10	PctRecentImmig	PctRecImmig5	PctRecImmig8	PctRecImmig10	PctSpeakEnglOnly	PctNotSpeakEnglWell	PctLargHouseFam	PctLargHouseOccup	PersPerOccupHous	PersPerOwnOccHous	PersPerRentOccHous	PctPersOwnOccup	PctPersDenseHous	PctHousLess3BR	MedNumBR	HousVacant	PctHousOccup	PctHousOwnOcc	PctVacantBoarded	PctVacMore6Mos	MedYrHousBuilt	PctHousNoPhone	PctWOFullPlumb	OwnOccLowQuart	OwnOccMedVal	OwnOccHiQuart	OwnOccQrange	RentLowQ	RentMedian	RentHighQ	RentQrange	MedRent	MedRentPctHousInc	MedOwnCostPctInc	MedOwnCostPctIncNoMtg	NumInShelters	NumStreet	PctForeignBorn	PctBornSameState	PctSameHouse85	PctSameCity85	PctSameState85	LemasSwornFT	LemasSwFTPerPop	LemasSwFTFieldOps	LemasSwFTFieldPerPop	LemasTotalReq	LemasTotReqPerPop	PolicReqPerOffic	PolicPerPop	RacialMatchCommPol	PctPolicWhite	PctPolicBlack	PctPolicHisp	PctPolicAsian	PctPolicMinor	OfficAssgnDrugUnits	NumKindsDrugsSeiz	PolicAveOTWorked	LandArea	PopDens	PctUsePubTrans	PolicCars	PolicOperBudg	LemasPctPolicOnPatr	LemasGangUnitDeploy	LemasPctOfficDrugUn	PolicBudgPerPop	murders	murdPerPop	rapes	rapesPerPop	robberies	robbbPerPop	assaults	assaultPerPop	burglaries	burglPerPop	larcenies	larcPerPop	autoTheft	autoTheftPerPop	arsons	arsonsPerPop	ViolentCrimesPerPop	nonViolPerPop
count	213.000000	213.000000	652.000000	6.520000e+02	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	6.520000e+02	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	6.520000e+02	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.00000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.00000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	652.000000	110.000000	110.000000	110.000000	110.000000	1.100000e+02	110.000000	110.000000	110.000000	110.000000	110.000000	110.000000	110.000000	110.000000	110.000000	110.000000	110.000000	110.000000	652.000000	652.000000	652.000000	110.000000	1.100000e+02	110.000000	110.000000	652.000000	110.000000	652.000000	652.000000	651.000000	651.000000	651.000000	651.000000	646.000000	646.000000	649.000000	649.000000	650.000000	650.000000	652.000000	652.000000	651.000000	651.000000	645.000000	647.000000
mean	19.215962	45170.629108	5.624233	5.946048e+04	2.855675	7.809647	77.526794	5.590368	18.911733	14.076104	27.651979	13.474862	10.642561	5.536025e+04	78.748129	38775.401840	80.323574	0.947699	42.681534	23.992347	7.033880	14.907301	44149.286810	17090.036810	18324.825153	13762.685583	14571.973926	15354.412577	10750.357362	11761.555215	7998.104294	10.885000	10.636656	23.483390	23.986012	6.171641	63.020828	16.390000	23.150000	12.702209	29.008221	8.804233	31.155844	12.393206	10.657147	3.253972	76.047853	72.412132	84.666319	77.069647	57.116626	65.847040	1931.239264	3.038865	1.137832e+04	13.715798	21.905031	30.579509	39.761610	2.179018	3.444632	4.747853	6.143037	75.763282	5.302960	7.452163	5.606672	2.780997	2.869233	2.612193	64.439525	7.83089	46.804586	2.579755	1797.153374	92.747883	62.434816	2.833482	32.559325	1964.822086	4.017209	0.500521	130855.375767	165164.895706	207417.072086	76561.696319	422.260736	535.31135	652.104294	229.843558	605.185583	27.204141	23.227301	13.182669	64.351227	25.808282	14.050905	54.592086	50.449969	76.195046	88.750890	386.645455	187.492182	328.300000	162.856455	2.316315e+05	94973.719909	548.017273	187.495455	83.070182	77.613000	7.260818	11.264182	1.458364	19.696182	19.381818	9.009091	131.661818	28.132362	3909.484509	4.185245	158.345455	2.768150e+07	87.694909	4.545455	0.994172	133338.572636	8.174847	6.437638	27.511521	32.601644	246.944700	200.858464	339.063467	395.167276	833.169492	1087.383436	2220.513846	3027.076031	652.769939	626.186319	38.989247	37.594240	633.092155	4771.453292
std	13.235541	23379.476968	2.891520	1.761253e+05	0.408726	11.403043	16.836132	7.078681	21.017267	3.468795	5.207060	4.374458	4.816070	1.771707e+05	39.884760	14992.840835	7.663542	0.720604	14.193613	8.329159	5.210186	4.670639	16305.422483	7518.350487	7664.944504	11781.611890	21453.858461	8306.152573	7484.655939	6152.004224	32504.649723	8.717475	9.042146	13.260618	13.906079	3.106506	8.291967	6.963107	6.493035	6.571939	10.689668	2.665646	7.469032	3.272733	2.920009	0.306269	9.115853	10.484327	10.127028	9.013849	7.681386	6.533787	9642.018433	2.968143	5.711001e+04	6.508180	9.211187	11.316008	13.783983	2.194139	3.377931	4.494551	5.832892	18.723682	6.274762	5.279596	4.428548	0.386238	0.347950	0.500160	15.662616	8.60621	16.396064	0.541450	6516.092183	5.937758	15.509878	3.600391	15.338566	10.768572	4.408227	0.548299	86051.081556	103692.962681	122233.431468	47804.118771	161.275321	188.10053	212.395831	86.642121	183.577918	2.978437	2.810971	1.903225	304.640980	172.904158	10.888643	12.661013	11.309996	10.228695	5.937045	920.540095	89.599880	825.405594	71.528482	5.986471e+05	56905.574568	320.126315	89.602001	12.075083	18.477372	10.003297	15.940309	2.661775	18.440615	42.284528	2.780982	100.500720	145.747217	4050.534161	5.706809	328.035477	5.733176e+07	9.596803	3.922732	2.635903	71346.126995	50.019629	8.563770	102.932993	29.623423	1633.680281	271.942800	1806.484322	362.778347	2758.257846	626.537587	7014.427370	1673.329990	2990.114617	605.970864	226.700972	43.713629	590.534673	2451.570076
min	1.000000	70.000000	1.000000	1.002300e+04	1.600000	0.000000	7.210000	0.060000	0.770000	4.580000	10.550000	4.930000	1.660000	0.000000e+00	0.000000	12908.000000	31.680000	0.000000	9.020000	4.810000	0.640000	3.460000	14257.000000	5237.000000	5472.000000	0.000000	0.000000	0.000000	0.000000	3188.000000	78.000000	0.730000	0.620000	2.520000	1.630000	1.610000	24.820000	3.060000	8.690000	1.370000	6.480000	2.350000	13.300000	4.490000	3.640000	2.500000	32.240000	26.110000	27.430000	30.640000	33.730000	44.650000	0.000000	0.000000	5.600000e+01	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	6.150000	0.000000	1.560000	0.480000	1.580000	1.610000	1.580000	13.930000	0.18000	3.060000	1.000000	36.000000	37.470000	16.860000	0.000000	3.120000	1939.000000	0.000000	0.000000	15700.000000	27200.000000	42200.000000	0.000000	99.000000	144.00000	226.000000	0.000000	192.000000	14.900000	15.300000	10.100000	0.000000	0.000000	0.510000	20.210000	11.830000	27.950000	49.800000	70.000000	47.030000	69.000000	25.280000	1.415500e+04	15370.900000	72.400000	47.000000	42.310000	1.600000	0.000000	0.000000	0.000000	0.000000	0.000000	1.000000	0.000000	0.900000	16.300000	0.000000	20.000000	4.288914e+06	35.010000	0.000000	0.000000	37041.600000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	1.000000	3.230000	6.000000	49.170000	75.000000	396.560000	1.000000	7.210000	0.000000	0.000000	15.030000	696.610000
25%	7.000000	25770.000000	3.000000	1.559650e+04	2.610000	1.275000	68.767500	1.237500	4.420000	12.057500	24.670000	11.310000	7.480000	1.098100e+04	93.325000	27160.250000	76.090000	0.507500	31.957500	18.327500	3.020000	11.850000	31316.250000	11933.250000	13198.250000	8311.250000	8240.250000	10678.250000	6863.750000	7624.250000	918.250000	4.085000	4.537500	13.067500	13.527500	3.877500	58.337500	11.707500	19.095000	8.050000	21.442500	6.897500	26.310000	10.047500	8.637500	3.070000	70.917500	65.840000	78.687500	72.522500	51.855000	62.030000	161.750000	1.120000	1.200750e+03	9.107500	15.642500	23.212500	30.422500	0.620000	1.027500	1.437500	1.955000	69.727500	1.317500	4.137500	3.000000	2.540000	2.657500	2.247500	54.685000	2.32000	36.037500	2.000000	332.750000	90.530000	53.177500	0.780000	19.875000	1957.000000	0.730000	0.180000	63825.000000	81975.000000	105050.000000	41600.000000	302.500000	387.00000	479.000000	162.000000	455.750000	24.975000	21.475000	11.700000	0.000000	0.000000	5.742500	45.632500	42.310000	70.985000	86.175000	126.000000	125.192500	107.250000	112.335000	5.000000e+04	56083.725000	341.925000	125.200000	76.587500	70.150000	1.602500	2.862500	0.000000	7.937500	6.000000	7.000000	60.725000	5.700000	1501.675000	0.577500	52.000000	7.804816e+06	85.490000	0.000000	0.000000	91056.775000	0.000000	0.000000	3.000000	11.870000	9.000000	44.015000	28.000000	128.790000	130.000000	640.120000	390.250000	1799.760000	41.000000	217.457500	2.000000	11.165000	231.480000	2941.910000
50%	21.000000	45990.000000	6.000000	2.676400e+04	2.795000	3.425000	81.355000	3.320000	10.785000	13.765000	27.245000	12.605000	10.210000	2.352500e+04	100.000000	36308.000000	80.370000	0.730000	42.265000	23.465000	5.475000	14.290000	41761.000000	15627.000000	16674.500000	12222.500000	12238.000000	14159.000000	9148.500000	10264.000000	2221.500000	7.805000	7.935000	21.550000	20.365000	5.380000	63.310000	15.795000	22.375000	12.075000	26.965000	8.805000	29.865000	12.605000	10.715000	3.200000	76.060000	72.680000	85.605000	77.460000	57.230000	66.560000	432.500000	2.210000	3.057500e+03	13.610000	21.710000	30.735000	40.180000	1.415000	2.320000	3.315000	4.205000	81.475000	2.835000	5.595000	4.130000	2.730000	2.855000	2.540000	64.350000	5.03500	47.845000	3.000000	612.000000	94.685000	62.340000	1.780000	30.815000	1966.000000	2.250000	0.350000	123500.000000	153200.000000	187550.000000	61600.000000	428.500000	544.50000	659.500000	215.000000	613.000000	27.300000	23.400000	12.700000	0.000000	0.000000	11.160000	53.800000	50.220000	78.245000	89.890000	161.000000	161.125000	140.000000	138.020000	7.524050e+04	80827.600000	450.950000	161.150000	85.965000	82.620000	3.345000	7.430000	0.095000	14.920000	9.000000	9.000000	110.600000	11.600000	2739.000000	2.005000	71.000000	1.194086e+07	89.910000	5.000000	0.000000	118573.900000	1.000000	3.995000	8.000000	24.610000	32.000000	106.070000	87.000000	277.020000	288.000000	983.410000	792.000000	2747.070000	131.500000	433.590000	8.000000	25.220000	461.980000	4520.890000
75%	27.000000	63360.000000	8.000000	5.233275e+04	3.040000	8.917500	90.522500	6.635000	23.905000	15.480000	29.767500	14.475000	13.220000	5.198125e+04	100.000000	46892.500000	85.520000	1.162500	53.237500	29.192500	9.740000	17.380000	53311.250000	20130.000000	21471.000000	16412.500000	16644.500000	18218.750000	12565.750000	14357.500000	5541.500000	16.092500	13.322500	30.955000	31.772500	7.840000	68.592500	20.272500	26.230000	15.917500	35.010000	10.650000	34.792500	14.675000	12.745000	3.370000	82.675000	80.325000	92.537500	83.150000	62.312500	70.330000	1200.750000	3.782500	7.961000e+03	17.505000	27.945000	38.275000	49.940000	3.172500	4.907500	6.905000	8.855000	88.545000	6.542500	8.932500	6.357500	2.972500	3.020000	2.880000	75.432500	9.87000	57.645000	3.000000	1284.500000	96.307500	72.920000	3.592500	43.257500	1973.000000	5.892500	0.620000	175700.000000	213775.000000	275850.000000	97925.000000	535.000000	655.00000	814.500000	282.250000	728.000000	29.100000	25.000000	14.200000	25.250000	2.000000	19.002500	63.002500	58.712500	83.455000	92.572500	237.500000	234.467500	207.000000	202.740000	1.575000e+05	118636.875000	687.550000	234.475000	92.090000	89.612500	9.262500	12.350000	1.985000	24.750000	19.000000	11.000000	161.750000	23.900000	4966.375000	5.677500	114.750000	1.813866e+07	93.045000	10.000000	0.000000	158150.800000	4.000000	8.850000	19.000000	45.155000	116.500000	238.850000	232.750000	580.935000	665.000000	1415.030000	1773.500000	3862.060000	409.500000	857.282500	21.000000	48.000000	833.290000	5927.930000
max	81.000000	93480.000000	10.000000	3.485398e+06	5.280000	89.950000	99.170000	57.460000	95.290000	43.380000	66.640000	55.320000	52.770000	3.485398e+06	100.000000	123625.000000	96.760000	6.320000	79.430000	76.390000	26.920000	45.510000	131315.000000	63302.000000	68850.000000	212120.000000	480000.000000	82133.000000	125526.000000	51320.000000	643809.000000	48.820000	49.890000	73.660000	73.630000	23.830000	83.810000	41.690000	62.670000	44.270000	64.970000	19.090000	71.260000	23.460000	19.100000	4.640000	93.600000	92.580000	100.000000	97.340000	78.870000	83.960000	212238.000000	24.190000	1.336665e+06	38.520000	54.190000	69.760000	78.740000	13.710000	19.930000	25.340000	32.630000	97.330000	38.330000	34.870000	30.870000	4.520000	4.480000	4.730000	96.140000	59.49000	95.340000	4.000000	109558.000000	99.000000	96.220000	39.890000	78.590000	1987.000000	23.630000	5.330000	500001.000000	500001.000000	500001.000000	267700.000000	1001.000000	1001.00000	1001.000000	675.000000	1001.000000	35.100000	32.700000	23.400000	4597.000000	3109.000000	60.400000	92.040000	76.440000	95.850000	99.900000	8295.000000	623.660000	7683.000000	383.830000	5.480855e+06	316432.500000	2156.500000	623.700000	100.000000	100.000000	59.520000	98.400000	18.570000	98.400000	406.000000	14.000000	439.100000	3569.800000	44229.900000	52.590000	2482.000000	4.880505e+08	99.410000	10.000000	18.420000	546841.190000	1076.000000	63.940000	1773.000000	170.670000	38415.000000	2264.130000	42437.000000	2191.730000	50232.000000	4848.970000	119092.000000	22164.780000	59764.000000	4968.590000	5119.000000	377.610000	3928.030000	27010.770000

	population	householdsize	racepctblack	racePctWhite	racePctAsian	racePctHisp	agePct12t21	agePct65up	pctUrban	medIncome	pctWFarmSelf	pctWInvInc	pctWPubAsst	pctWRetire	blackPerCap	indianPerCap	AsianPerCap	OtherPerCap	HispPerCap	PctPopUnderPov	PctLess9thGrade	PctBSorMore	PctEmplManu	PctEmplProfServ	PctOccupManu	MalePctDivorce	MalePctNevMarr	PctFam2Par	PctWorkMomYoungKids	PctImmigRecent	PctRecentImmig	PctPersOwnOccup	PctHousLess3BR	MedNumBR	PctHousOccup	PctVacantBoarded	PctVacMore6Mos	MedYrHousBuilt	PctWOFullPlumb	RentQrange	MedRentPctHousInc	MedOwnCostPctInc	MedOwnCostPctIncNoMtg	PctBornSameState	PctSameHouse85	PctSameState85	LandArea	PopDens	PctUsePubTrans	LemasPctOfficDrugUn	murdPerPop
count	1.919000e+03	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000	1919.000000
mean	5.222536e+04	2.710662	9.353835	83.515268	2.804054	8.673700	14.404299	12.009489	69.758046	33901.321001	0.884648	43.464356	6.773955	16.119192	11573.294424	12301.949453	14313.012507	9451.968213	11022.774883	11.685935	9.435503	22.991496	17.795654	24.504070	13.709792	9.176597	30.687061	73.977910	60.309349	13.662590	1.168708	65.509693	45.854846	2.623241	92.690594	2.780214	35.128588	1962.744659	0.433111	201.729026	26.362064	21.300834	13.033299	60.188791	51.336967	87.711407	28.031162	2815.384575	3.093622	1.007004	5.927712
std	2.051729e+05	0.347113	13.914794	16.325927	4.720112	15.388139	4.479374	4.847315	44.375875	13478.160054	0.688882	12.757634	4.474456	4.588814	9336.714385	15477.135843	9635.116167	8046.208476	5757.066299	8.451142	6.864861	12.521400	8.086259	6.650632	6.399682	2.806209	8.027055	10.302549	7.904721	9.680139	1.663076	14.131028	14.076144	0.519988	5.265741	3.447570	14.026619	11.160290	0.431390	87.361065	2.907053	2.948489	1.466011	17.074383	10.718396	7.488716	116.924373	2949.803130	4.957666	2.927262	9.038823
min	1.000500e+04	1.600000	0.000000	2.680000	0.060000	0.120000	4.580000	1.660000	0.000000	12908.000000	0.000000	9.020000	0.500000	3.460000	0.000000	0.000000	0.000000	0.000000	0.000000	0.640000	0.200000	1.630000	2.050000	8.690000	1.370000	2.130000	12.060000	32.240000	24.420000	0.000000	0.000000	13.930000	3.060000	1.000000	37.470000	0.000000	3.120000	1939.000000	0.000000	0.000000	14.900000	14.100000	10.100000	6.750000	11.830000	32.830000	0.900000	10.000000	0.000000	0.000000	0.000000
25%	1.430700e+04	2.490000	0.930000	75.885000	0.625000	0.950000	12.210000	8.875000	0.000000	23689.500000	0.470000	34.285000	3.370000	13.045000	6749.500000	6346.500000	8537.500000	5584.000000	7299.500000	4.650000	4.760000	14.080000	11.985000	20.080000	9.035000	7.130000	25.475000	67.710000	55.290000	6.965000	0.190000	56.435000	37.745000	2.000000	90.950000	0.770000	24.690000	1956.000000	0.170000	140.000000	24.400000	19.200000	11.900000	48.365000	44.635000	84.725000	7.200000	1177.650000	0.370000	0.000000	0.000000
50%	2.258000e+04	2.660000	3.070000	89.610000	1.260000	2.430000	13.620000	11.860000	100.000000	31231.000000	0.690000	42.440000	5.660000	15.740000	9787.000000	9874.000000	12408.000000	8182.000000	9703.000000	9.500000	7.900000	19.650000	16.670000	23.360000	13.020000	9.220000	29.080000	74.780000	60.610000	12.420000	0.540000	64.960000	46.790000	3.000000	93.990000	1.730000	34.470000	1964.000000	0.330000	175.000000	26.200000	21.400000	12.800000	62.080000	51.890000	89.620000	13.600000	2007.600000	1.240000	0.000000	2.420000
75%	4.308450e+04	2.855000	11.390000	95.965000	2.815000	8.910000	15.390000	14.545000	100.000000	41464.500000	1.100000	52.270000	9.100000	18.845000	14519.000000	14790.500000	17413.500000	11407.500000	13424.000000	17.040000	12.145000	28.910000	22.730000	27.605000	17.390000	11.130000	33.470000	81.775000	65.585000	18.035000	1.410000	75.390000	54.210000	3.000000	95.920000	3.510000	44.275000	1971.000000	0.560000	242.500000	28.100000	23.300000	13.800000	74.170000	58.650000	92.730000	25.350000	3284.800000	3.450000	0.000000	8.610000
max	7.322564e+06	5.280000	96.670000	99.630000	57.460000	95.290000	54.400000	52.770000	100.000000	123625.000000	6.530000	89.040000	26.920000	45.510000	212120.000000	480000.000000	106165.000000	137000.000000	54648.000000	48.820000	49.890000	73.630000	50.030000	62.670000	44.270000	19.090000	76.320000	93.600000	87.970000	64.290000	13.710000	96.590000	95.340000	4.000000	99.000000	39.890000	82.130000	1987.000000	5.330000	803.000000	35.100000	32.700000	23.400000	93.140000	78.560000	99.900000	3569.800000	44229.900000	54.330000	48.440000	91.090000

	state	pop_bins	householdsize_norm	racepctblack_bins	racePctWhite_bins	racePctAsian_bins	racePctHisp_bins	agePct12t21_norm	agePct65up_norm	pctUrban_bins	medIncome_bins	pctWFarmSelf_bins	pctWInvInc_norm	pctWPubAsst_bins	pctWRetire_norm	blackPerCap_bins	indianPerCap_bins	AsianPerCap_bins	OtherPerCap_bins	HispPerCap_bins	PctPopUnderPov_bins	PctLess9thGrade_bins	PctBSorMore_bins	PctEmplManu_norm	PctEmplProfServ_norm	PctOccupManu_norm	MalePctDivorce_norm	MalePctNevMarr_norm	PctFam2Par_bins	PctWorkMomYoungKids_norm	PctImmigRecent_bins	PctRecentImmig_bins	PctPersOwnOccup_norm	PctHousLess3BR_norm	MedNumBR_bins	PctHousOccup_bins	PctVacantBoarded_bins	PctVacMore6Mos_norm	MedYrHousBuilt_bins	PctWOFullPlumb_bins	RentQrange_bins	MedRentPctHousInc_norm	MedOwnCostPctInc_norm	MedOwnCostPctIncNoMtg_bins	PctBornSameState_bins	PctSameHouse85_norm	PctSameState85_bins	LandArea_bins	PopDens_bins	PctUsePubTrans_bins	murdPerPop_reg_target
0	NJ	10000-13500	0.407609	0.9-2.8%	90-96%	2.7-57.5%	0.9-2.2%	0.158370	0.189200	100%	42,000-$125,000	1.0-7.0%	0.764559	0-3%	0.355054	10000-15000	0-6500	17500-106500	0-5500	13500-55000	0-5%	5-8%	30-80	0.262609	0.372916	0.096037	0.090802	0.222845	82-95%	0.316916	7-12%	0.5-1.3%	0.937939	0.086693	2.5-4	96-99%	1.75-4%	0.435135	1956-1964	0.16-0.3%	230-805	0.440594	0.376344	13-14%	50-65%	0.801139	85-90%	0-7	1200-2000	0.5-50%	0.000000
1	PA	19000-29000	0.331522	0-0.8%	90-96%	2.7-57.5%	0.1-0.9%	0.129065	0.303659	100%	42,000-$125,000	1.0-7.0%	0.688453	0-3%	0.461118	15000-250000	0-6500	17500-106500	0-5500	1000-13500	0-5%	5-8%	19-30	0.212797	0.381438	0.117016	0.123821	0.247899	82-95%	0.420456	0-7%	0.2-0.5%	0.908541	0.222583	2.5-4	96-99%	0-0.75%	0.192507	1956-1964	0-0.16%	170-230	0.628713	0.354839	12-13%	75-95%	0.890754	93-100%	7-14	2000-3300	0.5-50%	0.000000
2	OR	29000-51500	0.225543	0-0.8%	90-96%	2.7-57.5%	0.9-2.2%	0.136090	0.168656	100%	$32,000-$42,000	1.0-7.0%	0.583729	0-3%	0.263971	15000-250000	15000-500000	12500-17500	5500-8000	7500-1000	0-5%	0-5%	30-80	0.289704	0.237681	0.172960	0.469929	0.213508	75-82%	0.655547	12-18%	0.5-1.3%	0.607912	0.481144	2.5-4	94-96%	0.75-1.75%	0.055942	1971-1987	0-0.16%	140-170	0.455446	0.408602	10-12%	0-50%	0.371197	32-85%	7-14	2000-3300	0.5-50%	0.091119
4	MO	515000-7500000	0.230978	0.9-2.8%	90-96%	0.6-1.2%	0.1-0.9%	0.271176	0.226961	100%	$8,000-$24,000	0.7-1.0%	0.401525	5-8%	0.252794	6500-10000	10000-15000	8500-12500	5500-8000	7500-1000	17-60%	8-12%	19-30	0.255523	0.336050	0.311189	0.546580	0.330843	67-70%	0.606452	18-65%	0.2-0.5%	0.530849	0.543238	0-2.5	91-94%	1.75-4%	0.292368	1964-1971	0.3-0.5%	0-140	0.569307	0.172043	10-12%	50-65%	0.456466	85-90%	26-4000	1200-2000	0.5-50%	0.050829
5	MA	19000-29000	0.271739	0.9-2.8%	96-100%	1.2-2.6%	0.9-2.2%	0.132276	0.249658	100%	42,000-$125,000	0-0.5%	0.483379	5-8%	0.327467	15000-250000	15000-500000	12500-17500	11500-137000	13500-55000	0-5%	0-5%	19-30	0.249479	0.342349	0.166200	0.226415	0.373327	75-82%	0.641070	7-12%	0.5-1.3%	0.613235	0.479952	2.5-4	94-96%	0.75-1.75%	0.396532	1939-1956	0.16-0.3%	230-805	0.470297	0.360215	12-13%	75-95%	0.773565	93-100%	7-14	2000-3300	0.5-50%	0.000000

	countyCode	communityCode	fold	population	householdsize	racepctblack	racePctWhite	racePctAsian	racePctHisp	agePct12t21	agePct12t29	agePct16t24	agePct65up	numbUrban	pctUrban	medIncome	pctWWage	pctWFarmSelf	pctWInvInc	pctWSocSec	pctWPubAsst	pctWRetire	medFamInc	perCapInc	whitePerCap	blackPerCap	indianPerCap	AsianPerCap	OtherPerCap	HispPerCap	NumUnderPov	PctPopUnderPov	PctLess9thGrade	PctNotHSGrad	PctBSorMore	PctUnemployed	PctEmploy	PctEmplManu	PctEmplProfServ	PctOccupManu	PctOccupMgmtProf	MalePctDivorce	MalePctNevMarr	FemalePctDiv	TotalPctDiv	PersPerFam	PctFam2Par	PctKids2Par	PctYoungKids2Par	PctTeen2Par	PctWorkMomYoungKids	PctWorkMom	NumKidsBornNeverMar	PctKidsBornNeverMar	NumImmig	PctImmigRecent	PctImmigRec5	PctImmigRec8	PctImmigRec10	PctRecentImmig	PctRecImmig5	PctRecImmig8	PctRecImmig10	PctSpeakEnglOnly	PctNotSpeakEnglWell	PctLargHouseFam	PctLargHouseOccup	PersPerOccupHous	PersPerOwnOccHous	PersPerRentOccHous	PctPersOwnOccup	PctPersDenseHous	PctHousLess3BR	MedNumBR	HousVacant	PctHousOccup	PctHousOwnOcc	PctVacantBoarded	PctVacMore6Mos	MedYrHousBuilt	PctHousNoPhone	PctWOFullPlumb	OwnOccLowQuart	OwnOccMedVal	OwnOccHiQuart	OwnOccQrange	RentLowQ	RentMedian	RentHighQ	RentQrange	MedRent	MedRentPctHousInc	MedOwnCostPctInc	MedOwnCostPctIncNoMtg	NumInShelters	NumStreet	PctForeignBorn	PctBornSameState	PctSameHouse85	PctSameCity85	PctSameState85	LemasSwornFT	LemasSwFTPerPop	LemasSwFTFieldOps	LemasSwFTFieldPerPop	LemasTotalReq	LemasTotReqPerPop	PolicReqPerOffic	PolicPerPop	RacialMatchCommPol	PctPolicWhite	PctPolicBlack	PctPolicHisp	PctPolicAsian	PctPolicMinor	OfficAssgnDrugUnits	NumKindsDrugsSeiz	PolicAveOTWorked	LandArea	PopDens	PctUsePubTrans	PolicCars	PolicOperBudg	LemasPctPolicOnPatr	LemasGangUnitDeploy	LemasPctOfficDrugUn	PolicBudgPerPop	murders	murdPerPop	rapes	rapesPerPop	robberies	robbbPerPop	assaults	assaultPerPop	burglaries	burglPerPop	larcenies	larcPerPop	autoTheft	autoTheftPerPop	arsons	arsonsPerPop	ViolentCrimesPerPop	nonViolPerPop
count	6.000000	6.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.00000	10.000000	10.00000	10.00000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.00000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.00000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.00000	10.000000	10.000000	10.00000	10.00000	10.000000	10.000000	10.000000	10.000000	10.000000	10.00000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.00000	10.00000	10.000000	10.000000	10.000000	10.000000	10.000000	10.00000	4.000000	4.000000	4.000000	4.000000	4.000000	4.000000	4.00000	4.000000	4.000000	4.000000	4.000000	4.000000	4.00000	4.000000	4.000000	4.00000	4.000000	10.000000	10.00000	10.000000	4.000000	4.000000e+00	4.000000	4.000000	10.000000	4.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	5.000000	5.000000	10.000000	5.000000
mean	36.000000	46991.666667	5.600000	130737.000000	2.644000	13.102000	80.219000	2.356000	2.900000	15.926000	31.567000	17.090000	8.383000	122225.900000	66.679000	34658.500000	83.24900	0.890000	53.73300	19.05700	6.652000	14.514000	40603.800000	16394.200000	18934.400000	11684.700000	10802.300000	11941.500000	7550.700000	11422.800000	16641.300000	10.43400	5.671000	15.547000	27.992000	5.550000	67.669000	10.500000	27.004000	9.710000	31.997000	11.131000	37.087000	14.195000	12.698000	3.070000	69.078000	66.923000	78.012000	71.999000	64.057000	72.826000	8707.900000	4.84600	9168.900000	16.070000	23.136000	32.390000	38.655000	0.826000	1.221000	1.694000	2.029000	91.849000	0.999000	4.577000	2.926000	2.478000	2.64700	2.272000	56.559000	3.66400	53.05900	2.500000	5759.800000	91.135000	52.967000	5.460000	37.11200	1962.100000	4.333000	0.703000	79560.000000	102790.000000	142730.000000	63170.000000	353.300000	458.800000	576.300000	223.000000	523.100000	25.580000	21.270000	12.57000	540.20000	21.400000	4.892000	45.596000	42.259000	72.017000	78.10500	1321.500000	321.770000	1195.500000	292.042500	342453.750000	103870.247500	467.72500	321.775000	93.342500	78.467500	18.317500	1.822500	0.84500	20.410000	57.250000	10.00000	110.825000	475.750000	2144.41000	5.266000	273.000000	6.771188e+07	91.565000	3.750000	1.568000	183933.272500	53.300000	13.211000	91.500000	62.496000	917.700000	250.089000	1187.900000	374.653000	2093.700000	1109.321000	6643.600000	4542.293000	1284.500000	463.628000	65.000000	29.056000	700.452000	6282.766000
std	67.441827	28123.129567	2.458545	195996.657595	0.183073	20.853535	21.288761	1.411486	1.969202	4.659438	6.288545	6.490518	3.757798	200855.131413	46.991043	8091.644803	5.91336	0.282921	17.13674	7.47369	2.777384	3.086009	7881.706186	2864.852131	6263.841867	4743.836166	3944.801165	3917.865894	4963.835637	3793.149462	30194.074621	5.25849	2.456413	6.050423	6.726027	1.799451	5.265294	7.166563	4.380231	2.491113	5.597257	2.143805	9.211694	2.128407	2.070452	0.110454	10.550211	13.091965	10.966617	10.505742	3.713286	4.229474	21871.270031	4.93539	18148.978878	7.175449	8.711964	9.665053	12.176344	0.594516	0.907738	1.151831	1.383598	2.375563	0.713621	1.920151	0.990311	0.159081	0.12979	0.180358	13.593108	2.54648	7.30352	0.527046	9292.176049	3.579349	13.167262	4.960423	9.26628	13.763478	2.358983	0.677004	16780.623747	21183.140571	47476.030209	39215.559554	73.063215	89.197409	110.048525	54.108944	86.992273	2.081559	1.263197	1.22479	1458.76613	41.414437	1.934378	14.947427	7.373137	9.247546	8.72826	2127.326413	332.327943	1917.553041	298.699678	376930.265812	47184.416303	263.97143	332.352317	4.302126	31.166043	30.793664	1.280478	1.24141	30.252446	94.026149	2.94392	85.098938	946.994925	2844.69981	11.358544	238.753709	9.423337e+07	2.175416	4.787136	2.240812	131168.014654	141.648273	25.019023	124.392971	31.185403	2215.698036	391.183905	2792.666167	484.606807	3763.327902	545.433585	10214.814233	1273.663253	2555.521397	447.962126	86.709284	14.479887	902.569245	2102.843563
min	1.000000	10675.000000	2.000000	12809.000000	2.420000	0.390000	29.600000	0.460000	0.450000	11.720000	24.660000	10.530000	3.480000	0.000000	0.000000	25434.000000	72.91000	0.420000	34.26000	9.30000	1.140000	10.970000	31083.000000	12984.000000	13023.000000	6507.000000	5974.000000	6598.000000	0.000000	7964.000000	453.000000	3.62000	2.810000	8.970000	18.340000	2.460000	59.670000	2.350000	21.640000	7.260000	23.610000	7.970000	28.450000	10.330000	9.280000	2.930000	41.960000	33.580000	52.230000	44.320000	58.430000	67.490000	124.000000	1.38000	473.000000	7.400000	8.880000	15.860000	15.860000	0.190000	0.230000	0.410000	0.410000	87.490000	0.110000	2.480000	1.780000	2.260000	2.50000	2.020000	31.880000	0.73000	45.87000	2.000000	259.000000	85.220000	31.090000	0.390000	25.00000	1939.000000	0.660000	0.250000	41600.000000	56700.000000	78000.000000	36400.000000	227.000000	299.000000	385.000000	155.000000	395.000000	23.700000	19.500000	10.90000	0.00000	0.000000	2.590000	25.240000	28.170000	52.730000	59.20000	91.000000	104.930000	83.000000	99.410000	40473.000000	42529.000000	193.40000	104.900000	89.390000	32.200000	0.000000	0.000000	0.00000	0.000000	2.000000	6.00000	0.000000	7.900000	10.00000	0.290000	29.000000	6.124758e+06	90.070000	0.000000	0.000000	86495.300000	0.000000	0.000000	3.000000	19.630000	0.000000	0.000000	1.000000	6.540000	117.000000	443.000000	370.000000	2420.830000	13.000000	85.060000	2.000000	5.850000	26.170000	3637.430000
25%	7.000000	23656.250000	4.000000	20360.250000	2.470000	0.670000	74.420000	1.580000	0.997500	12.987500	27.702500	12.900000	4.875000	2534.500000	17.205000	28699.750000	79.68000	0.775000	41.14250	12.14000	6.312500	12.342500	34943.250000	14207.750000	15437.500000	8634.500000	8367.500000	9472.000000	4290.750000	9250.250000	1632.250000	5.96000	3.557500	10.157500	23.682500	4.240000	63.130000	4.132500	22.905000	7.610000	28.460000	9.442500	30.772500	13.212500	11.452500	2.975000	66.645000	63.977500	76.795000	71.767500	61.520000	69.590000	329.250000	2.57500	766.500000	10.310000	17.052500	25.772500	30.862500	0.505000	0.860000	1.325000	1.507500	90.505000	0.567500	3.050000	1.950000	2.345000	2.53250	2.150000	47.117500	1.40500	47.82000	2.000000	622.750000	88.290000	43.382500	2.412500	32.25250	1949.750000	3.452500	0.287500	72875.000000	90350.000000	115875.000000	43800.000000	305.750000	403.500000	500.500000	180.750000	472.250000	24.075000	20.350000	11.60000	14.50000	0.250000	3.820000	35.297500	38.192500	68.627500	74.97000	222.250000	127.400000	209.750000	115.970000	90976.500000	88653.025000	352.32500	127.400000	89.742500	75.152500	3.105000	1.410000	0.00000	5.677500	10.250000	9.00000	70.950000	18.425000	474.45000	0.637500	136.250000	2.187468e+07	90.197500	0.000000	0.000000	108644.900000	0.000000	0.000000	9.750000	43.902500	3.250000	13.567500	14.250000	70.010000	142.500000	747.592500	728.750000	3678.982500	28.250000	142.757500	7.000000	24.230000	125.725000	5535.310000
50%	7.000000	55612.500000	5.500000	29236.500000	2.685000	3.760000	81.515000	1.965000	2.810000	13.750000	29.405000	14.555000	9.055000	20169.000000	98.985000	31670.500000	82.05500	0.865000	47.63500	20.44000	6.830000	13.645000	37157.000000	14936.500000	16479.500000	11166.500000	9841.000000	11700.000000	8708.500000	9801.500000	3000.000000	11.24500	5.315000	15.710000	27.575000	6.020000	68.585000	11.115000	27.390000	9.095000	31.565000	11.875000	33.380000	14.530000	13.190000	3.050000	72.870000	70.855000	78.900000	73.125000	63.930000	71.920000	775.500000	3.33000	1416.500000	14.225000	22.830000	32.600000	38.995000	0.700000	1.035000	1.480000	1.725000	92.520000	0.790000	4.510000	2.990000	2.455000	2.62500	2.235000	58.445000	3.29500	50.03000	2.500000	837.500000	92.130000	53.650000	4.065000	35.80500	1969.000000	4.360000	0.505000	84200.000000	111600.000000	143950.000000	56350.000000	346.000000	454.000000	583.000000	220.500000	508.000000	25.100000	21.400000	12.75000	48.00000	2.000000	4.505000	45.480000	42.560000	73.640000	78.64000	344.500000	184.395000	316.500000	167.410000	228905.500000	107817.950000	425.05000	184.400000	93.330000	90.835000	4.435000	2.225000	0.37500	8.110000	14.500000	10.50000	122.700000	35.400000	1100.80000	1.195000	236.500000	2.826889e+07	90.725000	2.500000	0.000000	136726.300000	1.000000	4.120000	25.500000	62.655000	43.500000	127.315000	88.500000	219.560000	251.000000	907.585000	1623.000000	4727.200000	84.000000	248.415000	11.000000	36.100000	461.230000	5712.280000
75%	17.500000	64937.500000	7.000000	179535.250000	2.777500	12.540000	96.972500	3.100000	4.787500	18.217500	34.950000	20.187500	10.740000	176090.500000	100.000000	41595.500000	88.58000	1.120000	62.96000	23.59750	8.122500	16.110000	47186.000000	19435.250000	21030.500000	13316.500000	13261.250000	14098.250000	10198.500000	12570.750000	13352.500000	12.46500	7.807500	18.045000	32.660000	6.422500	71.245000	14.332500	29.802500	11.115000	36.330000	12.895000	38.682500	15.995000	14.375000	3.172500	74.970000	73.390000	82.762500	77.340000	66.407500	75.075000	3705.500000	4.25750	9601.250000	21.602500	29.967500	37.975000	44.575000	0.940000	1.247500	1.572500	2.070000	92.725000	1.357500	5.300000	3.630000	2.620000	2.74750	2.385000	62.820000	5.22750	57.14750	3.000000	9001.250000	94.085000	58.750000	5.772500	41.64250	1971.750000	5.150000	0.760000	88600.000000	118750.000000	152350.000000	59500.000000	406.250000	514.250000	651.750000	270.500000	560.500000	25.850000	21.875000	13.10000	171.00000	26.250000	5.212500	57.707500	46.192500	77.885000	83.39250	1443.750000	378.765000	1302.250000	343.482500	480382.750000	123035.172500	540.45000	378.775000	96.930000	94.150000	19.647500	2.637500	1.22000	22.842500	61.500000	11.50000	162.575000	105.375000	2488.37500	3.132500	373.250000	7.410609e+07	92.092500	6.250000	2.852500	212014.672500	18.750000	13.750000	168.000000	80.992500	446.000000	258.875000	863.500000	477.072500	1565.000000	1458.805000	8562.250000	5570.495000	1100.500000	665.182500	105.000000	37.680000	874.262500	7276.460000
max	173.000000	79000.000000	10.000000	606900.000000	2.920000	65.840000	98.930000	4.820000	5.390000	26.330000	45.340000	32.370000	15.230000	606900.000000	100.000000	47924.000000	90.83000	1.270000	89.04000	33.08000	10.930000	21.120000	54088.000000	20125.000000	34563.000000	23000.000000	17500.000000	18666.000000	13713.000000	20971.000000	96278.000000	19.34000	9.560000	26.850000	39.120000	8.620000	75.000000	25.410000	33.610000	14.330000	40.150000	13.670000	55.640000	16.430000	15.030000	3.210000	77.390000	78.060000	95.600000	82.350000	69.420000	79.410000	70523.000000	18.20000	58887.000000	28.890000	36.960000	48.350000	57.550000	2.330000	3.590000	4.690000	5.580000	95.170000	2.550000	8.960000	4.600000	2.680000	2.84000	2.590000	74.490000	8.25000	67.33000	3.000000	28855.000000	95.240000	71.630000	17.400000	56.91000	1976.000000	8.200000	2.490000	98300.000000	123900.000000	258700.000000	172000.000000	454.000000	587.000000	736.000000	301.000000	664.000000	30.100000	23.500000	14.90000	4682.00000	131.000000	9.700000	67.860000	53.490000	84.460000	89.09000	4506.000000	813.360000	4066.000000	733.940000	871531.000000	157316.090000	827.40000	813.400000	97.320000	100.000000	64.400000	2.840000	2.63000	65.420000	198.000000	13.00000	197.900000	2686.900000	9538.90000	37.300000	590.000000	2.081850e+08	94.740000	10.000000	6.020000	375785.190000	454.000000	81.950000	324.000000	123.330000	7107.000000	1282.850000	9003.000000	1625.090000	11532.000000	2081.590000	31466.000000	6118.530000	8060.000000	1454.870000	200.000000	41.420000	3048.380000	9252.350000